© 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. 104575
    Prev
    Next
    INDEX
    Explanations

    case with, could move, Council of

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

    start with

    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
    on
    0.52
    ках
    0.46
    yen
    0.42
    onas
    0.42
    endem
    0.41
    f
    0.40
     журнали
    0.40
    c
    0.40
    journalist
    0.39
    m
    0.39
    POSITIVE LOGITS
     áreas
    0.52
     ビタミン
    0.50
     houdt
    0.49
    RestorePolicy
    0.49
     intérêts
    0.49
     yks
    0.48
     że
    0.48
    Doesn
    0.48
     która
    0.47
    iddel
    0.47
    Activations Density 0.000%

    No Known Activations