© 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. 110484
    Prev
    Next
    INDEX
    Explanations

    public static java declarations

    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
    鵙
    -1.53
     nôtre
    -1.53
    
    -1.51
     véhicule
    -1.48
    푆
    -1.46
    すっ
    -1.43
    ਫ਼
    -1.43
     aguj
    -1.42
     tohoto
    -1.41
    あぁ
    -1.41
    POSITIVE LOGITS
     void
    2.22
     final
    2.02
    final
    1.90
    void
    1.74
     in
    1.44
     only
    1.44
    ed
    1.34
    â
    1.34
     of
    1.33
     from
    1.32
    Activations Density 0.005%

    No Known Activations