© 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. 12303
    Prev
    Next
    INDEX
    Explanations

    countries, percentages, and lists

    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
    sivu
    -0.87
     process
    -0.84
     started
    -0.83
     aconse
    -0.82
    terus
    -0.81
    process
    -0.80
    不通
    -0.80
    ----</
    -0.79
     skóry
    -0.79
     proceso
    -0.78
    POSITIVE LOGITS
     jär
    1.05
     followed
    1.03
    followed
    1.01
    依旧
    1.00
     recensement
    0.93
     épaules
    0.93
     FormControl
    0.90
     oiseau
    0.89
     RANK
    0.87
    RANK
    0.85
    Activations Density 0.050%

    No Known Activations