© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31358
    Prev
    Next
    INDEX
    Explanations

    book reviews reader engagement

    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
    existsSync
    -0.96
     dziś
    -0.94
     району
    -0.93
    ern
    -0.91
    guna
    -0.90
     VARIABLES
    -0.89
    спонд
    -0.89
    슐
    -0.88
    uestamente
    -0.88
    '])){
    -0.88
    POSITIVE LOGITS
     readers
    1.70
     reader
    1.45
     Readers
    1.41
    Readers
    1.38
    readers
    1.30
     chapters
    1.22
    作者
    1.17
     Goodreads
    1.14
    Characters
    1.13
    reader
    1.13
    Activations Density 0.035%

    No Known Activations