© 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. 22-GEMMASCOPE-RES-131K
    7. 16748
    Prev
    Next
    INDEX
    Explanations

    code snippets and tags

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     but
    -1.04
     Mediterranean
    -0.91
     by
    -0.90
     with
    -0.88
     (
    -0.88
    勃
    -0.88
     to
    -0.87
     only
    -0.84
     solo
    -0.83
     即
    -0.83
    POSITIVE LOGITS
    vermectin
    0.92
    elni
    0.91
     empuj
    0.90
    redient
    0.90
    tamment
    0.88
     zimowa
    0.87
    Nachteile
    0.85
    셧
    0.85
     pequeñas
    0.85
    ţa
    0.85
    Activations Density 0.019%

    No Known Activations