© 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. 112527
    Prev
    Next
    INDEX
    Explanations

    highlighting key aspects

    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
    白衣
    -2.77
     esteemed
    -2.56
     marvelous
    -2.56
     amazingly
    -2.53
     formé
    -2.50
     selben
    -2.50
    —
    -2.48
     successes
    -2.44
     ก็
    -2.41
     immense
    -2.39
    POSITIVE LOGITS
    d
    3.64
    which
    2.83
    fying
    2.48
    n
    2.48
    Заключение
    2.42
    Выводы
    2.41
     ambayo
    2.34
    .
    2.25
    
    2.20
    乐观
    2.16
    Activations Density 0.005%

    No Known Activations