© 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. 34-GEMMASCOPE-RES-131K
    7. 93294
    Prev
    Next
    INDEX
    Explanations

    body-parser

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

    The neuron strongly signals on multi‐syllable, domain-specific content words (technical or specialized jargon).

    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
    駅から
    -0.74
     Australia
    -0.70
     Sierra
    -0.69
    erton
    -0.67
    жуть
    -0.67
     intégral
    -0.67
    Australia
    -0.66
     midt
    -0.66
     habit
    -0.66
     past
    -0.65
    POSITIVE LOGITS
    ---|
    0.73
     Wład
    0.70
    +--
    0.69
    TestTools
    0.68
     coger
    0.67
     эле
    0.65
    Бил
    0.65
     salarios
    0.65
    RadioGroup
    0.63
     WORKS
    0.63
    Activations Density 0.031%

    No Known Activations