© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78666
    Prev
    Next
    INDEX
    Explanations

    metadata labels like title

    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
     rám
    -0.94
     nép
    -0.87
    histo
    -0.86
    irà
    -0.84
     Formel
    -0.84
    ellón
    -0.83
     those
    -0.83
    riotic
    -0.82
     очки
    -0.82
    {(-
    -0.81
    POSITIVE LOGITS
    Afficher
    0.95
     tutela
    0.95
    飒
    0.94
     Title
    0.94
     comanda
    0.91
     Afric
    0.91
     title
    0.90
     ilyen
    0.86
    VARIANT
    0.85
    すすめ
    0.85
    Activations Density 0.002%

    No Known Activations