© 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. 56888
    Prev
    Next
    INDEX
    Explanations

    religious concepts and scriptures

    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
    matem
    -0.81
    transformers
    -0.75
     denkt
    -0.73
    頂き
    -0.71
     Hivatalos
    -0.71
    crom
    -0.69
    헬
    -0.68
    magne
    -0.67
     JsonResult
    -0.67
    ansons
    -0.66
    POSITIVE LOGITS
     Regis
    0.91
    ս
    0.82
    rrer
    0.80
     Micah
    0.77
    ifer
    0.77
    довых
    0.76
     alan
    0.75
    ското
    0.75
    vyš
    0.73
     stalk
    0.72
    Activations Density 0.100%

    No Known Activations