© 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. 34-GEMMASCOPE-RES-131K
    7. 50471
    Prev
    Next
    INDEX
    Explanations

    body-parser version

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

    The neuron strongly activates on occurrences of the token “body” (e.g. in “body-parser”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     bula
    -0.73
    Jîn
    -0.72
     interna
    -0.72
     biolog
    -0.71
    Median
    -0.70
     bawah
    -0.70
    klady
    -0.70
     mf
    -0.69
    галда
    -0.69
    Domic
    -0.68
    POSITIVE LOGITS
    ophilic
    0.68
    Fotografía
    0.67
    actic
    0.67
     protectora
    0.67
    分別
    0.66
    thra
    0.65
     течение
    0.65
    PHONY
    0.65
    allis
    0.64
    штей
    0.64
    Activations Density 0.076%

    No Known Activations