© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43612
    Prev
    Next
    INDEX
    Explanations

    C++ header files

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

    This neuron lights up on tokens that are part of mixed‐case or uppercase identifiers (e.g. CamelCase library/class/function names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     from
    -1.67
     Geschä
    -1.55
     like
    -1.48
     ursprünglich
    -1.48
     ouvriers
    -1.47
     such
    -1.45
     Eigentum
    -1.44
     with
    -1.41
     cojín
    -1.41
     presumed
    -1.35
    POSITIVE LOGITS
    \
    1.38
     milliard
    1.36
     Xunit
    1.30
     custos
    1.26
     nomme
    1.25
     Inſ
    1.24
     النبات
    1.23
    лую
    1.23
     malgré
    1.23
     título
    1.21
    Activations Density 0.007%

    No Known Activations