© 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. 528
    Prev
    Next
    INDEX
    Explanations

    describing ways that

    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
     to
    -1.97
     at
    -1.63
     resultMap
    -1.34
    libat
    -1.32
    brasil
    -1.30
     recent
    -1.29
    milan
    -1.26
     errMsg
    -1.23
    :
    -1.20
     from
    -1.19
    POSITIVE LOGITS
     که
    1.61
    ковых
    1.52
    "،
    1.41
    诓
    1.41
    5
    1.40
     cuando
    1.40
     когда
    1.39
    艫
    1.38
    艄
    1.34
    arities
    1.32
    Activations Density 0.030%

    No Known Activations