© 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. 10-GEMMASCOPE-RES-131K
    7. 13915
    Prev
    Next
    INDEX
    Explanations

    links and list items

    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_10/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
    <bos>
    -1.73
    graphique
    -1.61
     Vorschriften
    -1.60
    asanjo
    -1.54
    зить
    -1.50
     该
    -1.50
    mêmes
    -1.48
     {
    -1.45
     Scritto
    -1.45
    thalten
    -1.44
    POSITIVE LOGITS
    "
    1.57
     integrates
    1.55
    an
    1.53
    ],
    1.52
    m
    1.49
     także
    1.46
    他能
    1.44
    된
    1.44
    in
    1.43
     '
    1.42
    Activations Density 0.000%

    No Known Activations