© 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. 15654
    Prev
    Next
    INDEX
    Explanations

    discussion of treaties, needs, tools, roles, invitations, hugs, perceived flaws

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

    The neuron identifies floating‐point numeric tokens (numbers with decimal points).

    oai_token-act-pair · o4-miniTriggered 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
     compounded
    0.79
     conceptually
    0.79
    ディース
    0.77
    フロ
    0.75
     accad
    0.74
    エ
    0.74
    ユニ
    0.73
    ユ
    0.72
     canonically
    0.72
    Contin
    0.71
    POSITIVE LOGITS
    вых
    0.77
     Bedrooms
    0.75
     beraber
    0.75
     ввода
    0.73
     Freshwater
    0.72
     открыть
    0.71
     Firth
    0.71
    nykh
    0.71
    tones
    0.70
     Fisheries
    0.70
    Activations Density 0.000%

    No Known Activations