© 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. 7293
    Prev
    Next
    INDEX
    Explanations

    popular culture

    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
     '
    -1.73
     andere
    -1.66
     they
    -1.58
     il
    -1.58
     for
    -1.54
     le
    -1.52
     us
    -1.52
    ра
    -1.51
    皛
    -1.50
     таких
    -1.49
    POSITIVE LOGITS
    Можно
    1.80
    グルト
    1.77
    涷
    1.72
    鵟
    1.68
    jących
    1.67
    नलोड
    1.66
    欵
    1.64
    partimento
    1.63
    Только
    1.61
     estekak
    1.59
    Activations Density 0.014%

    No Known Activations