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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 3672
    Prev
    Next
    INDEX
    Explanations

    bodybuilding and weightlifting

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

    fitness and bodybuilding-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_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
    怎么回事
    -1.75
     Then
    -1.73
     stran
    -1.69
    自从
    -1.63
    '}}>
    -1.57
    喽
    -1.53
    şört
    -1.53
    iertas
    -1.52
    什麼
    -1.51
     入っ
    -1.51
    POSITIVE LOGITS
     We
    2.09
    ?”
    2.06
     ?
    1.94
    ’
    1.92
     để
    1.89
     сумка
    1.88
    ↵↵
    1.85
    }$.
    1.84
    ”、“
    1.84
    Ꭳ
    1.83
    Activations Density 0.006%

    No Known Activations