© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32695
    Prev
    Next
    INDEX
    Explanations

    license terms and copyright notices

    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
     ваши
    -0.83
     вашу
    -0.75
    uš
    -0.75
     segue
    -0.75
    ued
    -0.74
    medo
    -0.73
    Noch
    -0.73
     taw
    -0.72
     fie
    -0.72
     EXCHANGE
    -0.72
    POSITIVE LOGITS
     unparalleled
    0.75
     garner
    0.72
    dataSource
    0.70
     душу
    0.70
    名稱
    0.69
    RDONLY
    0.68
     analyzing
    0.68
     despite
    0.68
    ņas
    0.68
    하여
    0.66
    Activations Density 0.037%

    No Known Activations