© 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. 64032
    Prev
    Next
    INDEX
    Explanations

    book publisher information

    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
     control
    -0.88
     Messing
    -0.76
     reveal
    -0.76
    ัจ
    -0.73
    mende
    -0.72
    vature
    -0.72
    hung
    -0.71
    ؼ
    -0.71
     tool
    -0.71
    一旦
    -0.71
    POSITIVE LOGITS
     Publisher
    1.04
     book
    0.98
    Publisher
    0.97
     publishers
    0.95
     publisher
    0.94
    publisher
    0.90
    binding
    0.87
     Dimensions
    0.84
    isbn
    0.83
     spine
    0.81
    Activations Density 0.029%

    No Known Activations