© 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. 34-GEMMASCOPE-RES-131K
    7. 30123
    Prev
    Next
    INDEX
    Explanations

    bil + obalade, ox, inear, ateral, as

    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
    Negative Logits
     amico
    -0.82
     wait
    -0.73
    чется
    -0.71
    twe
    -0.70
    ía
    -0.70
     Newer
    -0.67
    距離
    -0.66
     ナ
    -0.66
     newer
    -0.66
     bancaria
    -0.66
    POSITIVE LOGITS
     Bil
    1.07
    Bil
    0.91
    bil
    0.83
    еня
    0.79
     OX
    0.78
     bil
    0.78
    mendation
    0.77
     FTE
    0.76
     눈
    0.73
     пев
    0.73
    Activations Density 0.023%

    No Known Activations