© 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. 720
    Prev
    Next
    INDEX
    Explanations

    coder and NSCoder

    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
     ‘
    -3.25
    ).
    -2.75
    蹀
    -2.73
     trock
    -2.64
     taki
    -2.63
    s
    -2.63
    并未
    -2.58
     assorted
    -2.55
    颡
    -2.48
    随即
    -2.45
    POSITIVE LOGITS
     sorella
    2.95
     figlia
    2.61
    ר
    2.55
    geſ
    2.55
    ه
    2.50
     dětí
    2.47
    瑀
    2.45
     ventured
    2.44
    er
    2.41
    骥
    2.41
    Activations Density 0.006%

    No Known Activations