© 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. 56681
    Prev
    Next
    INDEX
    Explanations

    route definitions and code comments

    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
    ?");
    -0.67
     ứng
    -0.66
     осна
    -0.66
     handles
    -0.65
    Pure
    -0.65
    ToolStrip
    -0.64
     csrf
    -0.63
    瑟
    -0.63
     sinto
    -0.63
    Vila
    -0.62
    POSITIVE LOGITS
    marvin
    0.72
    aites
    0.71
    iburg
    0.70
    duit
    0.69
    fontein
    0.69
     Sergeant
    0.69
     liked
    0.68
     DC
    0.68
     Wege
    0.68
     Benefits
    0.68
    Activations Density 0.069%

    No Known Activations