© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 71891
    Prev
    Next
    INDEX
    Explanations

    development of, epilepsy

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

    width values in markup code or user interface elements.

    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_22/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
    ffiche
    -1.48
    Править
    -1.34
     évé
    -1.31
     粉色
    -1.30
    zdo
    -1.25
    corde
    -1.24
     reseña
    -1.24
     inteligentes
    -1.21
    ampe
    -1.20
    でもあります
    -1.20
    POSITIVE LOGITS
     a
    1.48
    al
    1.43
    le
    1.36
    ing
    1.35
    na
    1.32
    7
    1.22
     \\
    1.21
    n
    1.20
    on
    1.19
    ak
    1.17
    Activations Density 0.000%

    No Known Activations