© 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. 29729
    Prev
    Next
    INDEX
    Explanations

    train more and more

    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
    я
    0.55
     started
    0.52
    aving
    0.48
    ن
    0.46
    imbra
    0.45
    install
    0.44
    asset
    0.44
    start
    0.44
    inizio
    0.44
    elle
    0.43
    POSITIVE LOGITS
     ჩვენ
    0.52
     oprac
    0.48
     Surely
    0.48
    写作
    0.47
     Ñ
    0.46
     нам
    0.46
     Handwriting
    0.46
     Subsidiary
    0.45
     умно
    0.45
     हमारी
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.