© 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. 694
    Prev
    Next
    INDEX
    Explanations

    webinar or seminar

    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
    夲
    -2.63
    และ
    -2.44
    🫅
    -2.42
    ⚢
    -2.41
    ruguay
    -2.39
    attutto
    -2.38
     můžete
    -2.38
    榖
    -2.36
    摠
    -2.36
     và
    -2.34
    POSITIVE LOGITS
    e
    2.89
    </strong>
    2.72
    on
    2.63
     ”
    2.59
    >
    2.53
    M
    2.52
     …
    2.45
    ܜ
    2.42
    <i>
    2.39
    un
    2.39
    Activations Density 0.003%

    No Known Activations