© 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. 106242
    Prev
    Next
    INDEX
    Explanations

    code, license, version, copyright

    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
    مزید
    -0.73
     singularities
    -0.71
     REFERENCE
    -0.67
    ghold
    -0.67
     Yamaguchi
    -0.66
    kamp
    -0.64
    казать
    -0.64
     Background
    -0.64
    icace
    -0.64
    료
    -0.63
    POSITIVE LOGITS
    ocyclic
    0.75
    Bands
    0.68
    utie
    0.65
    плуата
    0.64
    观点
    0.63
    Td
    0.63
    ના
    0.62
     freshman
    0.62
     szkole
    0.61
    警察
    0.61
    Activations Density 0.075%

    No Known Activations