© 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. 4291
    Prev
    Next
    INDEX
    Explanations

    HTML tags and punctuation

    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
    bred
    -0.90
     there
    -0.86
     their
    -0.80
    raa
    -0.79
    ței
    -0.79
    𖣔
    -0.79
     its
    -0.78
     wer
    -0.77
     légère
    -0.77
    ścia
    -0.77
    POSITIVE LOGITS
    <blockquote>
    0.77
     grama
    0.76
     muur
    0.73
    delingen
    0.73
     perez
    0.72
    אי
    0.72
     Zelt
    0.72
    Dorf
    0.72
     cef
    0.72
     durability
    0.72
    Activations Density 0.017%

    No Known Activations