© 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. 48112
    Prev
    Next
    INDEX
    Explanations

    Section titles and item beginnings

    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
     galo
    -0.82
     curls
    -0.80
     gom
    -0.78
     zaś
    -0.78
    Corr
    -0.77
    这一点
    -0.77
     furi
    -0.76
    gone
    -0.75
     Kono
    -0.75
    वल
    -0.74
    POSITIVE LOGITS
    हाय
    0.85
    独自
    0.85
     thereunder
    0.79
    Thy
    0.77
     escultura
    0.76
    弐
    0.76
     приня
    0.76
     bekannten
    0.75
     měli
    0.75
     privaten
    0.74
    Activations Density 0.007%

    No Known Activations