© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110568
    Prev
    Next
    INDEX
    Explanations

    white

    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_34/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
    älä
    -0.80
    ͅ
    -0.79
    UserService
    -0.78
    gucigalpa
    -0.73
     mực
    -0.70
    ♝
    -0.70
    ể
    -0.70
     nonlinear
    -0.70
     hiel
    -0.69
     tirada
    -0.68
    POSITIVE LOGITS
     white
    6.13
    white
    5.00
     White
    4.16
    白
    4.13
    White
    4.13
    WHITE
    4.13
     WHITE
    4.00
     whites
    3.94
     白
    3.17
     سفید
    3.17
    Activations Density 0.121%

    No Known Activations