© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 70064
    Prev
    Next
    INDEX
    Explanations

    medical conditions

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

    ellipsis points and formatting elements in document structure like page breaks and indentation.

    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_34/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
     décé
    -1.29
     compéti
    -1.25
     légitime
    -1.24
     réjou
    -1.23
     fréquent
    -1.22
    Sudah
    -1.20
    Apre
    -1.20
    ときの
    -1.20
     éte
    -1.20
    Dá
    -1.18
    POSITIVE LOGITS
     of
    2.67
     to
    1.95
     into
    1.66
     for
    1.63
     are
    1.63
     by
    1.56
     also
    1.53
     (
    1.46
    ),
    1.45
     in
    1.44
    Activations Density 0.029%

    No Known Activations