© 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. 118902
    Prev
    Next
    INDEX
    Explanations

    field of view

    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
    Fauna
    -0.75
    outes
    -0.73
    原始内容存档于
    -0.73
     нале
    -0.73
     mendat
    -0.70
    IMDb
    -0.69
    toh
    -0.68
     грузо
    -0.68
     mentiras
    -0.67
    Stealth
    -0.66
    POSITIVE LOGITS
     view
    2.20
     FOV
    2.19
    FOV
    1.93
     field
    1.71
    fov
    1.70
     views
    1.61
    Fo
    1.58
     Field
    1.52
    view
    1.50
     Fo
    1.45
    Activations Density 0.074%

    No Known Activations