© 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. 62373
    Prev
    Next
    INDEX
    Explanations

    code, definition, import

    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
    放大
    -0.70
     International
    -0.70
     puts
    -0.69
     international
    -0.68
     abdominal
    -0.67
    لوب
    -0.67
     registration
    -0.66
    momentum
    -0.66
     Registration
    -0.66
     tử
    -0.66
    POSITIVE LOGITS
     جبل
    0.72
     zlat
    0.70
    eniging
    0.68
    sigt
    0.66
    tats
    0.66
    ╫
    0.66
    gezogen
    0.65
    atl
    0.65
     sbag
    0.63
     pokoj
    0.63
    Activations Density 0.111%

    No Known Activations