© 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. 2251
    Prev
    Next
    INDEX
    Explanations

    code block delimiters

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

    The neuron fires on standalone numerals (number tokens).

    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
    0.61
    if
    0.52
     coba
    0.51
     try
    0.51
    //
    0.50
    try
    0.50
     bilangan
    0.48
    <0x0D>
    0.47
     eventual
    0.46
    <unused60>
    0.43
    POSITIVE LOGITS
    UNCIL
    0.57
    ᅵ
    0.55
     रोपवे
    0.54
    remarkable
    0.54
    Concini
    0.54
    REIB
    0.53
    leun
    0.53
     اعلی
    0.52
    fiere
    0.52
     अपराधी
    0.51
    Activations Density 0.000%

    No Known Activations