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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6167
    Prev
    Next
    INDEX
    Explanations

    all followed by a continuation

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

    The neuron strongly activates on emphatic discourse‐introductory phrases starting a sentence—especially common sentence-opening words like “All,” “Tells,” or similar emphatic lead-ins.

    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
    daki
    1.26
    theless
    0.87
    ılan
    0.87
    いた
    0.85
    り
    0.84
    ם
    0.80
    ج
    0.77
    니다
    0.77
    holung
    0.76
    Alles
    0.75
    POSITIVE LOGITS
     wares
    0.74
     iż
    0.74
    கிறது
    0.66
    না
    0.66
    iteracy
    0.66
    옇
    0.65
     şi
    0.64
    ergic
    0.64
     equaliser
    0.64
    讽
    0.64
    Activations Density 0.000%

    No Known Activations