© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3359
    Prev
    Next
    INDEX
    Explanations

    type followed by symbol

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    moral
    -0.73
    voort
    -0.66
    BED
    -0.65
     AGO
    -0.65
     relation
    -0.65
     determination
    -0.65
    硕
    -0.64
     Ciò
    -0.63
    mahami
    -0.63
     Upgrades
    -0.62
    POSITIVE LOGITS
     ö
    0.76
     Kas
    0.74
    唾
    0.69
     بازی
    0.67
     kas
    0.67
    $.
    0.66
     אנ
    0.66
     모
    0.66
     stort
    0.65
     בה
    0.65
    Activations Density 0.073%

    No Known Activations