© 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. 110593
    Prev
    Next
    INDEX
    Explanations

    event handlers and UI properties

    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
    lohn
    -0.97
    ሩ
    -0.93
     chocs
    -0.93
    GRAND
    -0.91
     lada
    -0.90
     Temporada
    -0.89
    ፉ
    -0.88
     Grazie
    -0.88
     jaya
    -0.87
     CHLOR
    -0.87
    POSITIVE LOGITS
     Click
    1.00
    Visible
    0.98
    Click
    0.98
     will
    0.97
    ay
    0.95
    A
    0.94
     Work
    0.89
    𝑛
    0.89
     When
    0.87
     /*
    0.86
    Activations Density 0.001%

    No Known Activations