© 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. 11268
    Prev
    Next
    INDEX
    Explanations

    programming code and contexts

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

    underscores in programming code, particularly in function names and identifiers.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on code identifiers—especially function, method, or hook names that use underscores.

    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
     then
    -1.70
    olingo
    -1.61
    ᯾
    -1.55
    стота
    -1.48
    際の
    -1.47
     нови
    -1.45
    tifying
    -1.44
    metery
    -1.44
     синий
    -1.44
    frequently
    -1.41
    POSITIVE LOGITS
     your
    1.55
    asının
    1.38
     высоким
    1.38
    </i>
    1.34
     (
    1.33
     the
    1.33
     cocinar
    1.33
     standard
    1.32
    Pendidikan
    1.28
     herramientas
    1.27
    Activations Density 0.005%

    No Known Activations