© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 216312
    Prev
    Next
    INDEX
    Explanations

    journal citations

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

    reporting and analytics

    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
    t
    0.48
    お手
    0.46
     anum
    0.46
    する方法
    0.46
    的方法
    0.46
     bhfu
    0.45
    秘
    0.45
    }));
    0.44
    리소스
    0.44
    する場合は
    0.43
    POSITIVE LOGITS
    olk
    0.54
    okin
    0.53
    veck
    0.52
    hsl
    0.51
    olen
    0.49
    aring
    0.49
    fahr
    0.48
     наз
    0.47
    ali
    0.47
    Austral
    0.47
    Activations Density 0.000%

    No Known Activations