© 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. 195797
    Prev
    Next
    INDEX
    Explanations

    finally, having, to

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

    analyze thisaccept thekey featurescoached guyslarge city

    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
     তাহা
    0.53
    spr
    0.52
    année
    0.50
    я
    0.49
    ḿ
    0.49
     года
    0.48
    $?
    0.48
    includes
    0.48
    月份
    0.48
    íj
    0.47
    POSITIVE LOGITS
     throttle
    0.49
     motility
    0.48
    م
    0.46
     Trent
    0.45
     Thro
    0.45
     Helmholtz
    0.45
     Southampton
    0.45
     totem
    0.44
     many
    0.43
     revi
    0.43
    Activations Density 0.000%

    No Known Activations