© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16773
    Prev
    Next
    INDEX
    Explanations

    example. decline. yet. cards. for. bio

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     盗
    -0.93
    로그램
    -0.86
    ROR
    -0.85
    flasche
    -0.85
     комната
    -0.82
    mitir
    -0.81
    stoel
    -0.80
    سن
    -0.79
     जीवन
    -0.78
     คา
    -0.78
    POSITIVE LOGITS
     
    0.84
    !
    0.83
    росло
    0.79
    感が
    0.79
    ことが
    0.76
     Greater
    0.75
    Autoritní
    0.74
     ресурсов
    0.73
     pregunto
    0.73
    )
    0.73
    Activations Density 0.280%

    No Known Activations