© 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. 118778
    Prev
    Next
    INDEX
    Explanations

    Docket numbers and default visibility

    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
    Cloud
    -0.81
     formal
    -0.77
    соб
    -0.73
     into
    -0.71
     Entscheidung
    -0.71
    ynchron
    -0.69
    ynchro
    -0.69
     formality
    -0.68
    NESOTA
    -0.68
     uninterrupted
    -0.67
    POSITIVE LOGITS
     instance
    1.01
    instance
    0.90
    Instance
    0.89
     Instance
    0.87
     Defaults
    0.87
    default
    0.86
    Économie
    0.85
    INSTANCE
    0.84
     soyez
    0.84
     Storey
    0.82
    Activations Density 0.003%

    No Known Activations