© 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. 110628
    Prev
    Next
    INDEX
    Explanations

    programming method calls

    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
    riller
    -0.77
     erw
    -0.74
    Caribbean
    -0.72
     sweeteners
    -0.69
     لپ
    -0.68
     cuivre
    -0.68
    uran
    -0.68
     Berkshire
    -0.67
    charCodeAt
    -0.66
     microcontroller
    -0.66
    POSITIVE LOGITS
    toko
    0.80
    أت
    0.77
     Cebuano
    0.74
     morgan
    0.74
    LiveData
    0.73
    magna
    0.73
    nione
    0.73
    Ć
    0.73
    Dimensi
    0.72
    ХО
    0.71
    Activations Density 0.008%

    No Known Activations