© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100762
    Prev
    Next
    INDEX
    Explanations

    proper nouns, names, titles

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     anthem
    -1.17
    ⤞
    -1.13
     jin
    -1.13
     anesthe
    -1.11
     legt
    -1.11
     jdbcTemplate
    -1.10
    Polic
    -1.10
     impediment
    -1.10
     into
    -1.09
     Inquiry
    -1.09
    POSITIVE LOGITS
     fragile
    1.27
    部队
    1.27
    To
    1.25
     process
    1.24
    řízení
    1.23
     pietre
    1.23
     njego
    1.22
    zetek
    1.22
     costly
    1.21
    颪
    1.20
    Activations Density 0.067%

    No Known Activations