© 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. 34-GEMMASCOPE-RES-131K
    7. 94023
    Prev
    Next
    INDEX
    Explanations

    npm, outfit, sensitive

    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
    rosoft
    -0.84
     يُ
    -0.83
     passive
    -0.82
    Dolly
    -0.82
    absl
    -0.79
    忘れ
    -0.78
    द्धि
    -0.78
     Olive
    -0.77
     หรือ
    -0.77
    omina
    -0.76
    POSITIVE LOGITS
     EventEmitter
    0.92
     xrange
    0.91
    vinyl
    0.82
     jade
    0.79
     Hoodie
    0.79
    lowercase
    0.79
    coffee
    0.78
     världen
    0.78
     glyphicon
    0.77
    tionally
    0.76
    Activations Density 0.152%

    No Known Activations