© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1762
    Prev
    Next
    INDEX
    Explanations

    consequenceconclusionresult

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on discourse‐level connective adverbs (e.g. “thereby,” “thus,” “therefore,” “also,” “therefore”) that signal logical consequence or transition.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    the word "thereby" or phrases connecting cause and consequence using "and thus" or "therefore".

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    causal connective phrases that signal a result or consequence in the discourse.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    },
    0.57
    아
    0.57
     대신
    0.55
    5
    0.54
    사이트
    0.53
     detto
    0.52
     ovvero
    0.51
     그는
    0.50
    ⬥
    0.50
    роз
    0.50
    POSITIVE LOGITS
     poten
    0.71
     potentially
    0.67
     impregn
    0.57
     familiarize
    0.57
     belki
    0.54
     employability
    0.54
     regain
    0.54
    potentially
    0.53
     implant
    0.52
     পাবার
    0.52
    Activations Density 0.001%

    No Known Activations