© 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. 76092
    Prev
    Next
    INDEX
    Explanations

    0 and 1 sequences punctuated

    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
     oleh
    -0.89
     spécial
    -0.85
    uminous
    -0.79
    𝒻
    -0.77
     roupas
    -0.77
     problemática
    -0.77
     mesmo
    -0.77
     versione
    -0.77
     renk
    -0.76
    нализ
    -0.76
    POSITIVE LOGITS
     nonzero
    1.01
     tampoco
    0.88
    nonzero
    0.83
     hast
    0.78
    承认
    0.78
    とは思
    0.73
    แม
    0.73
    estroyer
    0.72
    zep
    0.72
    Any
    0.72
    Activations Density 0.043%

    No Known Activations