© 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. 244151
    Prev
    Next
    INDEX
    Explanations

    listing

    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
     olhos
    0.54
     occhi
    0.53
    лору
    0.52
     immobili
    0.52
     통한
    0.52
    重
    0.52
     imageHeight
    0.50
    ああ
    0.50
    гри
    0.49
     때문에
    0.49
    POSITIVE LOGITS
     Rogers
    0.63
     Rodgers
    0.57
     The
    0.55
     Central
    0.52
     Pittsburgh
    0.50
    id
    0.49
     UNESCO
    0.48
    u
    0.48
     They
    0.48
     Gardner
    0.48
    Activations Density 0.001%

    No Known Activations