© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86259
    Prev
    Next
    INDEX
    Explanations

    Map, Full, dependencies

    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
    merken
    -1.91
     ſte
    -1.73
    橚
    -1.71
     avendo
    -1.66
     HAVING
    -1.65
     Sección
    -1.59
    ǟ
    -1.58
     toujours
    -1.57
    wendige
    -1.54
    richtig
    -1.50
    POSITIVE LOGITS
     both
    2.11
     other
    1.93
     t
    1.77
    On
    1.73
     R
    1.73
     T
    1.73
    Both
    1.73
     those
    1.72
     any
    1.71
     may
    1.70
    Activations Density 0.164%

    No Known Activations