© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 112598
    Prev
    Next
    INDEX
    Explanations

    using or creating

    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
    çou
    -1.77
    rfan
    -1.75
    usually
    -1.70
    mainly
    -1.66
    fies
    -1.66
    hirts
    -1.66
    aning
    -1.63
    蛱
    -1.60
    ḿ
    -1.59
    蟥
    -1.59
    POSITIVE LOGITS
     has
    2.14
     had
    1.86
     have
    1.76
     creates
    1.73
     in
    1.71
     ....
    1.70
     and
    1.67
     gives
    1.66
     .....
    1.63
     so
    1.63
    Activations Density 0.174%

    No Known Activations