© 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. 34-GEMMASCOPE-RES-131K
    7. 110591
    Prev
    Next
    INDEX
    Explanations

    SQL default values

    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
     not
    -1.20
    OrNull
    -0.95
    ситет
    -0.89
    夫妇
    -0.86
    いいのか
    -0.85
    　　「
    -0.84
    вного
    -0.82
    Джерело
    -0.80
    Specifik
    -0.80
    价比
    -0.80
    POSITIVE LOGITS
    default
    1.14
     default
    1.05
    Default
    1.01
    Temporary
    0.90
     Default
    0.84
    temporary
    0.83
    gehenden
    0.83
     komment
    0.82
    DefaultValue
    0.81
    řeba
    0.81
    Activations Density 0.003%

    No Known Activations