© 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. 88547
    Prev
    Next
    INDEX
    Explanations

    technology systems

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

    visual content and related concepts

    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
     sitten
    0.49
     sullen
    0.48
    深圳市
    0.48
    Hvis
    0.47
     vody
    0.44
     hvis
    0.44
    的
    0.44
    mäßig
    0.44
     സെക്ര
    0.43
     dyslex
    0.43
    POSITIVE LOGITS
     божомол
    0.44
    tableName
    0.40
     impegn
    0.40
    ostasis
    0.39
    耱
    0.39
    sprite
    0.38
     оз
    0.38
    icions
    0.38
    statusCode
    0.37
     یار
    0.37
    Activations Density 0.000%

    No Known Activations