© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99612
    Prev
    Next
    INDEX
    Explanations

    digits mixed with numbers

    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
     the
    -3.23
    出来て
    -2.30
     dört
    -2.28
     Näch
    -2.17
    出来た
    -2.17
    années
    -2.16
    0
    -2.14
    癀
    -2.11
    柠
    -2.11
    vestres
    -2.09
    POSITIVE LOGITS
    1
    4.19
    I
    2.63
    桫
    2.45
    ?»
    2.45
    !»
    2.45
    ING
    2.42
    )/
    2.42
    ?");
    2.39
    垸
    2.38
    䛗
    2.38
    Activations Density 0.476%

    No Known Activations