© 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. 10-GEMMASCOPE-RES-131K
    7. 123841
    Prev
    Next
    INDEX
    Explanations

    how to understand

    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_10/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
    每
    -1.49
     некоторые
    -1.40
     не
    -1.38
    <blockquote>
    -1.37
     dona
    -1.36
    ——”
    -1.32
     certaine
    -1.28
     each
    -1.27
     époux
    -1.26
     compagnon
    -1.23
    POSITIVE LOGITS
     that
    2.17
     any
    1.96
     която
    1.63
     dokonce
    1.60
     puede
    1.56
    有任何
    1.55
    bufio
    1.53
     pueden
    1.53
    場所に
    1.49
     or
    1.43
    Activations Density 0.063%

    No Known Activations