© 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. 1786
    Prev
    Next
    INDEX
    Explanations

    can be

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

    This neuron almost exclusively fires on the very first token of a new paragraph or block of text.

    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
    檚
    0.89
     squint
    0.89
    тэй
    0.89
    sächlich
    0.87
     যদি
    0.84
     buildTypes
    0.84
     روح
    0.84
     calcareous
    0.84
    sí
    0.82
     didSet
    0.82
    POSITIVE LOGITS
    情况
    0.86
    r
    0.82
    ر
    0.79
     présente
    0.73
    （
    0.71
    erà
    0.71
     établie
    0.70
    鸯
    0.70
    р
    0.70
    <0xE3>
    0.70
    Activations Density 0.000%

    No Known Activations