© 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. 10-GEMMASCOPE-RES-131K
    7. 85451
    Prev
    Next
    INDEX
    Explanations

    identifying names

    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
    窶
    -1.99
     คา
    -1.94
     cementerio
    -1.88
    karena
    -1.85
     景色
    -1.83
    tentu
    -1.81
     dwóch
    -1.80
    richtig
    -1.77
    *?
    -1.77
    футболка
    -1.70
    POSITIVE LOGITS
    .
    3.09
     still
    2.27
    !
    2.17
    .”
    2.14
    m
    2.14
    .“
    2.13
     Remember
    2.11
    us
    2.00
     (“
    1.98
    ‘
    1.97
    Activations Density 0.143%

    No Known Activations