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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 613
    Prev
    Next
    INDEX
    Explanations

    hex color values

    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
    er
    -2.08
    on
    -2.03
     oculta
    -2.00
    at
    -1.95
    t
    -1.87
     gestaltet
    -1.83
    ra
    -1.81
    {
    -1.73
    i
    -1.73
    ha
    -1.68
    POSITIVE LOGITS
    9
    2.55
    !"
    2.45
     gesunde
    2.27
     Rücksicht
    2.23
     breite
    2.16
     vorigen
    2.14
     tiefe
    2.14
     klarer
    2.13
     vorliegenden
    2.11
    '
    2.08
    Activations Density 0.004%

    No Known Activations