© 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. 79245
    Prev
    Next
    INDEX
    Explanations

    brood eggs

    np_acts-logits-general · gemini-2.5-flash-lite

    punctuation marks and syntax elements in code and technical documents.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    Not in Any Lists

    No Comments

    Negative Logits
     compa
    -0.75
     velour
    -0.72
    stb
    -0.71
     vinaigrette
    -0.68
     McCarty
    -0.68
    MANUEL
    -0.67
     appeti
    -0.65
    Aran
    -0.64
     fortification
    -0.64
     sweatshirt
    -0.63
    POSITIVE LOGITS
     early
    0.81
    に参加
    0.75
    탈
    0.72
     Tiny
    0.71
     chaired
    0.69
     Range
    0.67
     Early
    0.66
    rose
    0.66
     Xing
    0.66
    ես
    0.65
    Activations Density 0.081%

    No Known Activations