© 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. 10-GEMMASCOPE-RES-131K
    7. 72310
    Prev
    Next
    INDEX
    Explanations

    names, medical terms, titles, Uuid

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

    medical conditions and technical terms, particularly those related to diseases or technical identifiers.

    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
    咈
    -3.22
    𖤣
    -3.08
    mpagne
    -2.97
     thrives
    -2.81
    餿
    -2.77
    ꪹ
    -2.72
    薷
    -2.72
     biała
    -2.70
     ſou
    -2.69
    嚶
    -2.69
    POSITIVE LOGITS
    as
    3.63
    to
    3.19
    i
    3.13
    for
    2.91
    \\
    2.80
     '
    2.66
     …
    2.63
    3
    2.44
    ,
    2.44
    ︓
    2.41
    Activations Density 0.009%

    No Known Activations