© 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. 123742
    Prev
    Next
    INDEX
    Explanations

    names and question indicators

    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
    ."
    -2.56
    </em>
    -2.11
    However
    -1.77
    '
    -1.77
    ,"
    -1.76
    These
    -1.73
    再度
    -1.72
     =
    -1.66
    This
    -1.66
     of
    -1.65
    POSITIVE LOGITS
    一点点
    1.84
    所谓的
    1.70
     almac
    1.70
     ........
    1.70
     quita
    1.68
     ujedno
    1.64
     ancha
    1.60
    踯
    1.59
     knji
    1.59
     ADDITIONAL
    1.57
    Activations Density 0.003%

    No Known Activations