© 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. 22030
    Prev
    Next
    INDEX
    Explanations

    Udacity, MBC, names, periodontitis

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

    proper nouns and acronyms, particularly organization names, universities, and medical/technical abbreviations.

    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
    渽
    -3.14
    ي
    -2.83
    鮠
    -2.69
    which
    -2.63
    其妙
    -2.48
    Ⲉ
    -2.45
    lapping
    -2.41
     ней
    -2.38
    その
    -2.36
    話の
    -2.34
    POSITIVE LOGITS
    たまた
    2.72
    on
    2.53
     οπο
    2.45
     culmination
    2.45
     But
    2.44
    
    2.42
     setCode
    2.36
    櫪
    2.27
    ing
    2.27
    灩
    2.25
    Activations Density 0.027%

    No Known Activations