© 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. 35329
    Prev
    Next
    INDEX
    Explanations

    el, aches, ense, ed/in, action

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

    javascript, python, web related terms

    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
    r
    1.67
    ну
    1.29
    that
    1.23
    the
    1.16
    ны
    1.14
    s
    1.13
    1
    1.13
    should
    1.09
    m
    1.09
    la
    1.06
    POSITIVE LOGITS
    cción
    0.98
    cco
    0.96
    instellungen
    0.92
    volent
    0.89
    getic
    0.88
    konom
    0.88
    ffekt
    0.87
    ktiv
    0.84
    czki
    0.84
    chten
    0.82
    Activations Density 0.329%

    No Known Activations