Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 452
    Prev
    Next
    INDEX
    Explanations

    team names and scores

    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
    Setelah
    -1.55
    酲
    -1.51
     the
    -1.51
     réunions
    -1.49
     séjours
    -1.47
     écout
    -1.44
     vœux
    -1.41
     wijze
    -1.40
    besar
    -1.39
     Voyez
    -1.38
    POSITIVE LOGITS
    x
    2.03
    </h2>
    2.02
    D
    1.93
    p
    1.89
    il
    1.82
    z
    1.75
    B
    1.74
    b
    1.71
    v
    1.70
    l
    1.70
    Activations Density 0.010%

    No Known Activations