© 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. 137163
    Prev
    Next
    INDEX
    Explanations

    regions, Island, region, artists, NIC, code area

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

    see below

    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
     H
    0.63
     Binary
    0.61
     T
    0.59
     g
    0.58
     M
    0.56
     Waterfront
    0.55
     sắt
    0.55
     PvP
    0.55
     Motorcycle
    0.55
     tog
    0.54
    POSITIVE LOGITS
    replaceable
    0.58
    remain
    0.56
    애
    0.50
    явление
    0.48
    ре
    0.48
    inov
    0.47
    ق
    0.47
    இந்நிலையில்
    0.47
    unknown
    0.47
    ኔታ
    0.47
    Activations Density 0.000%

    No Known Activations