© 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. 57002
    Prev
    Next
    INDEX
    Explanations

    fish and fishing

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

    references to marine and freshwater fish and fishing-related terms.

    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
    сіб
    -0.96
     terres
    -0.90
     estimat
    -0.85
     carcasses
    -0.82
     chao
    -0.82
     prodig
    -0.82
     relig
    -0.82
     加入
    -0.81
    טח
    -0.80
     solem
    -0.79
    POSITIVE LOGITS
     fish
    1.23
     predatory
    1.03
     fight
    1.02
    Fish
    0.95
     swim
    0.90
    ън
    0.88
     Fight
    0.85
     Fish
    0.85
     sought
    0.84
     swimming
    0.82
    Activations Density 0.014%

    No Known Activations