© 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. 220822
    Prev
    Next
    INDEX
    Explanations

    groups of people and things

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

    documentation strings and code examples

    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
    ing
    0.61
     тяжё
    0.51
    agua
    0.48
     pesante
    0.46
     Attack
    0.46
     Armour
    0.46
    n
    0.46
     Ang
    0.46
    forall
    0.45
     מר
    0.45
    POSITIVE LOGITS
     движения
    0.46
     chamado
    0.45
    बीटी
    0.44
    ཥ
    0.44
     называ
    0.44
    称为
    0.44
    财务
    0.44
    𐰚
    0.44
    ැ
    0.43
    ارا
    0.43
    Activations Density 0.000%

    No Known Activations