© 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. 22-GEMMASCOPE-RES-131K
    7. 11325
    Prev
    Next
    INDEX
    Explanations

    list items or conditions

    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_22/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
    ㍉
    -1.06
    实习
    -1.05
    第一时间
    -1.05
     drugi
    -1.04
    dijual
    -1.03
     liczby
    -0.97
     vicinity
    -0.96
    τερ
    -0.96
    負担
    -0.95
     funciones
    -0.94
    POSITIVE LOGITS
     when
    1.23
    ru
    1.13
    ang
    1.09
           
    1.08
    '
    1.05
    il
    1.04
    semantics
    1.03
    care
    1.01
    re
    1.01
    <u>
    1.01
    Activations Density 0.019%

    No Known Activations