© 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. 223380
    Prev
    Next
    INDEX
    Explanations

    service costs

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

    production, monitoring, design

    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
    咶
    0.56
     সিগারে
    0.54
     Проци
    0.53
    лата
    0.53
    批发
    0.53
    芡
    0.53
     результатом
    0.53
    טא
    0.52
    夶
    0.52
     AppBsky
    0.52
    POSITIVE LOGITS
    *
    0.66
    ↵
    0.64
    h
    0.63
    p
    0.57
    ion
    0.56
    um
    0.56
    t
    0.54
    un
    0.54
    ↵↵↵
    0.53
    e
    0.53
    Activations Density 0.000%

    No Known Activations