© 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. 85609
    Prev
    Next
    INDEX
    Explanations

    et cetera and et al

    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
    C
    -2.95
    禤
    -2.52
    a
    -2.28
    ER
    -2.27
     mein
    -2.25
    3
    -2.23
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -2.19
    i
    -2.19
    ↵↵↵↵↵↵↵↵↵↵↵
    -2.09
    ねぇ
    -2.09
    POSITIVE LOGITS
     whatnot
    2.58
    yskland
    2.38
     comparisons
    2.31
    旆
    2.28
    помним
    2.25
    uyler
    2.23
    *
    2.23
    demographic
    2.22
    嚆
    2.22
    です
    2.17
    Activations Density 0.016%

    No Known Activations