© 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. 210977
    Prev
    Next
    INDEX
    Explanations

    list of stores

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

    various types of regulation

    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
     conceptions
    0.52
     semelhante
    0.47
    .”.
    0.46
    .{
    0.45
     occupation
    0.44
     husband
    0.44
    .”
    0.44
     και
    0.43
     reich
    0.43
    ێ
    0.43
    POSITIVE LOGITS
     వివిధ
    0.53
     использование
    0.49
    会自动
    0.46
     પ્ર
    0.45
     다양한
    0.45
     бону
    0.45
     журнала
    0.45
     भरोसा
    0.44
    원은
    0.44
     Коми
    0.44
    Activations Density 0.000%

    No Known Activations