© 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. 71863
    Prev
    Next
    INDEX
    Explanations

    initialisms and acronyms

    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
    which
    -2.44
     encontram
    -2.39
    that
    -2.27
    誒
    -2.16
    mpagne
    -2.09
    麪
    -2.03
     podrían
    -2.00
    鹛
    -1.98
     Käufer
    -1.94
    遢
    -1.94
    POSITIVE LOGITS
    栳
    2.19
    เกง
    2.17
     andere
    2.17
    ?<
    2.03
     ?
    2.02
    芣
    2.00
    s
    1.95
    ࿚
    1.83
    亊
    1.82
     escuchado
    1.75
    Activations Density 0.027%

    No Known Activations