© 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. 10003
    Prev
    Next
    INDEX
    Explanations

    sorting and code timers

    np_acts-logits-general · gemini-2.5-flash-lite

    the token "UINT" in C/C++ code or "%%" in various programming contexts (batch scripts, Erlang comments).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     weiße
    -3.19
    们的
    -3.09
     eigentliche
    -2.89
     größte
    -2.73
     blaue
    -2.72
     klassische
    -2.64
    好在
    -2.63
     schwarze
    -2.58
     mittlere
    -2.52
    那时
    -2.47
    POSITIVE LOGITS
    y
    4.44
    」，
    3.50
    as
    2.97
    r
    2.95
    or
    2.66
    been
    2.59
     falle
    2.55
    there
    2.55
     perdana
    2.53
     manches
    2.50
    Activations Density 0.003%

    No Known Activations