© 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. 232906
    Prev
    Next
    INDEX
    Explanations

    routes to

    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
     diploid
    0.48
     grave
    0.47
     hereditary
    0.45
     countries
    0.44
    Partido
    0.44
    enegro
    0.42
    ገ
    0.40
     ধরা
    0.39
    Report
    0.39
    Order
    0.38
    POSITIVE LOGITS
     Rafał
    0.54
     выяс
    0.53
    uchar
    0.51
    왁
    0.49
     Flinders
    0.48
    颤
    0.47
    acı
    0.47
    OpportunitiesBy
    0.47
     wówczas
    0.46
    காற்று
    0.46
    Activations Density 0.001%

    No Known Activations