© 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. 782
    Prev
    Next
    INDEX
    Explanations

    prefix/suffix patterns

    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
    ，“
    -2.61
    (“
    -2.48
    '
    -2.39
    、“
    -2.06
     fordi
    -2.06
    ,“
    -2.00
    nitř
    -1.93
    on
    -1.93
    ;”
    -1.90
    本当に
    -1.88
    POSITIVE LOGITS
    ).
    2.83
    </strong>
    2.81
    </h2>
    2.56
     â
    2.20
     also
    2.20
    ：「
    2.11
    ."
    2.09
    缑
    2.09
    0
    2.08
    酲
    2.08
    Activations Density 0.004%

    No Known Activations