© 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. 611
    Prev
    Next
    INDEX
    Explanations

    goodwill and positive feelings

    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
    瘊
    -2.69
    皲
    -2.50
    ⸫
    -2.47
    罴
    -2.33
    轳
    -2.30
    
    -2.28
     buscan
    -2.27
    ఙ
    -2.23
     魅力
    -2.20
     fatiga
    -2.19
    POSITIVE LOGITS
    e
    2.83
    的
    2.70
    A
    2.50
    --
    2.28
    a
    2.25
    ）
    2.20
    ）.
    2.19
    大的
    2.13
    1.95
    We
    1.95
    Activations Density 0.001%
    No Known Activations