© 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. 84074
    Prev
    Next
    INDEX
    Explanations

    pursuant to, shipped from, permission from

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

    specific descriptions like house or lake

    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
     Foundation
    0.56
    :
    0.55
     multivariate
    0.54
     leaving
    0.53
     (
    0.52
     Society
    0.49
     LE
    0.49
     Leaving
    0.48
     —
    0.48
     Commission
    0.48
    POSITIVE LOGITS
    PlatformTarget
    0.50
    ِس
    0.47
    اعر
    0.46
     ailleurs
    0.46
    婚姻
    0.45
    وء
    0.44
    זי
    0.44
    ینو
    0.43
    部屋
    0.43
    ک
    0.43
    Activations Density 0.001%

    No Known Activations