© 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. 28996
    Prev
    Next
    INDEX
    Explanations

    programming functions and keywords

    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
    鳎
    -2.55
    ities
    -2.41
     mujer
    -2.22
    𖣘
    -2.19
     giddy
    -2.19
     auf
    -2.19
    当然
    -2.14
     bague
    -2.14
     куку
    -2.13
    唉
    -2.13
    POSITIVE LOGITS
    烀
    2.98
    an
    2.69
    𞤤
    2.47
    諏
    2.44
    猡
    2.39
    即便是
    2.36
    縂
    2.31
     occaf
    2.25
    ness
    2.20
     Inſ
    2.20
    Activations Density 0.003%

    No Known Activations