© 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. 44738
    Prev
    Next
    INDEX
    Explanations

    medically, statistically, or clinically modifications

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

    adverbs ending with 'ally' or 'ically', particularly scientific or medical terminology.

    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
     of
    -2.45
    iteness
    -1.91
    虓
    -1.88
    urably
    -1.82
     teknologi
    -1.76
    𖡼
    -1.73
     tiga
    -1.71
    PostInfinity
    -1.68
    fraid
    -1.64
     وش
    -1.63
    POSITIVE LOGITS
    0
    2.02
    '
    1.94
     salvajes
    1.68
     発表
    1.67
     zodat
    1.67
     only
    1.66
    "
    1.66
    re
    1.62
     समीक्षाएं
    1.61
     wydaje
    1.61
    Activations Density 0.093%

    No Known Activations