© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113032
    Prev
    Next
    INDEX
    Explanations

    configuration

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

    the word "Config" in programming code, particularly when it appears as part of class names, variable names, or configuration-related identifiers.

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

    The neuron fires on code identifiers or type names containing “Config” (e.g. Config, Configuration).

    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
    ᠂
    -2.92
    
    -2.67
    
    -2.61
    that
    -2.58
    and
    -2.56
    饜
    -2.50
     raiſ
    -2.50
    seamnă
    -2.47
    硨
    -2.47
    ŚCI
    -2.38
    POSITIVE LOGITS
    ﮦ
    2.58
    полне
    2.48
     หรือ
    2.39
    Ⲉ
    2.39
    S
    2.30
     indah
    2.27
    ༑
    2.27
    部分が
    2.25
     \
    2.22
    ﮯ
    2.22
    Activations Density 0.003%

    No Known Activations