© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7222
    Prev
    Next
    INDEX
    Explanations

    scientific classification and terminology

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

    words ending in "logic" or related academic/scientific terminology with suffixes like "ische", "ческое" in different languages.

    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_10/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
    e
    -1.88
    ࿙
    -1.83
    呜呜
    -1.80
    }
    -1.78
    ла
    -1.73
    ).
    -1.70
     According
    -1.68
     Depending
    -1.67
     Both
    -1.62
     It
    -1.61
    POSITIVE LOGITS
    
    1.80
     gegangen
    1.76
    ﮨ
    1.71
    な感じ
    1.65
     wesentlichen
    1.64
    
    1.64
     schlaf
    1.62
     nhưng
    1.61
     apoio
    1.60
     sorgfäl
    1.60
    Activations Density 0.077%

    No Known Activations