© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 116617
    Prev
    Next
    INDEX
    Explanations

    function, model, replace

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

    Portal, Pricing, WordPress, Python, Photographs, Restaurants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    ^{\
    0.53
    <sup>
    0.50
    ,\
    0.47
    er
    0.46
    ^{
    0.44
    ing
    0.44
     ${
    0.43
     MAR
    0.43
    _{\
    0.42
    \
    0.42
    POSITIVE LOGITS
     função
    0.50
     funkci
    0.49
     célula
    0.49
     funkce
    0.48
    modelo
    0.47
     odmah
    0.47
     atualização
    0.47
     Inicial
    0.46
    PTI
    0.46
     vervangen
    0.46
    Activations Density 0.003%

    No Known Activations