© 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. 173305
    Prev
    Next
    INDEX
    Explanations

    system, team, flood, We, its, Commune

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

    stemming, camera movement, joke, non-believer, compliancy technically

    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
     षटके
    0.55
     পারিত
    0.52
    unjukkan
    0.52
    𒅗
    0.52
     न्याया
    0.51
    MDEwOlJlcG
    0.51
    athan
    0.51
     Пока
    0.49
     النسب
    0.49
     沒有
    0.49
    POSITIVE LOGITS
    -
    0.55
    (
    0.55
    ,
    0.53
     dressing
    0.51
    .
    0.48
     stamp
    0.47
    :
    0.47
     coat
    0.47
     overw
    0.46
     processing
    0.46
    Activations Density 0.000%

    No Known Activations