© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 583
    Prev
    Next
    INDEX
    Explanations

    foreign languages and programming context

    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
     because
    -2.41
     for
    -2.02
     also
    -1.96
     to
    -1.82
     If
    -1.77
     schönes
    -1.75
     ganzes
    -1.70
     that
    -1.69
     This
    -1.69
    )))))
    -1.65
    POSITIVE LOGITS
     of
    3.30
    ers
    2.00
     impos
    1.90
    </h2>
    1.80
    犼
    1.69
    styleUrls
    1.66
     alimente
    1.66
     immense
    1.65
    новь
    1.65
    K
    1.63
    Activations Density 0.017%

    No Known Activations