© 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. 22-GEMMASCOPE-RES-131K
    7. 12347
    Prev
    Next
    INDEX
    Explanations

    He wrote or Q:

    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_22/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
    itting
    -0.95
    bew
    -0.95
    様な
    -0.94
    miesz
    -0.93
     hivyo
    -0.92
    vriende
    -0.92
    nend
    -0.91
     ucha
    -0.91
    timis
    -0.88
    cussed
    -0.87
    POSITIVE LOGITS
    を
    1.07
     we
    0.97
    弔
    0.84
     progressBar
    0.83
    requestBody
    0.83
    せっかく
    0.82
     ακόμα
    0.79
     maxWidth
    0.78
    法則
    0.77
    調味料
    0.77
    Activations Density 0.002%

    No Known Activations