© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 69122
    Prev
    Next
    INDEX
    Explanations

    mapping `##id##` to values

    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
    IVER
    -0.76
    货物
    -0.75
     версия
    -0.73
    Lew
    -0.73
    руйте
    -0.72
     Roumanie
    -0.72
     kao
    -0.71
    ᵈ
    -0.71
     Define
    -0.71
     ла
    -0.70
    POSITIVE LOGITS
     given
    0.88
     references
    0.87
     expressed
    0.82
     tokoh
    0.78
     referenced
    0.78
    くれます
    0.78
     referring
    0.77
    glyphicon
    0.77
    promises
    0.76
     promises
    0.75
    Activations Density 0.112%

    No Known Activations