© 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. 10023
    Prev
    Next
    INDEX
    Explanations

    programming function definition keyword

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

    the word "func" in programming code contexts.

    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
    潆
    -3.03
    觏
    -3.02
    jaqueta
    -3.02
    ︓
    -2.78
    colgante
    -2.73
     wodurch
    -2.70
    辚
    -2.67
    烀
    -2.59
    悫
    -2.59
    罴
    -2.56
    POSITIVE LOGITS
    y
    4.06
    the
    3.33
    1
    3.00
    7
    2.78
    \
    2.78
    We
    2.75
    b
    2.73
    2
    2.59
    In
    2.58
    er
    2.56
    Activations Density 0.007%

    No Known Activations