© 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. 96501
    Prev
    Next
    INDEX
    Explanations

    learn what happens

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

    foreign language ownership/campaigns

    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
    t
    0.46
     &
    0.45
    0
    0.45
    ^{-
    0.43
    .
    0.43
     -
    0.42
    ;
    0.42
     ,
    0.41
     ravine
    0.40
    T
    0.40
    POSITIVE LOGITS
     fundraising
    0.63
     kanyang
    0.63
     அவரது
    0.62
    ponsorship
    0.61
     jego
    0.56
     ايضا
    0.56
     hänen
    0.55
     ungdom
    0.55
    她的
    0.55
     fundación
    0.55
    Activations Density 0.001%

    No Known Activations