© 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. 30326
    Prev
    Next
    INDEX
    Explanations

    parse SQL, XML, git, url

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

    The neuron fires on occurrences of “parse” (in any casing or as part of identifiers/functions), i.e. tokens related to parsing.

    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
     Lait
    -0.94
    ཀ
    -0.88
     sequenced
    -0.84
     Slope
    -0.83
    WEAPON
    -0.82
    computed
    -0.81
    السكان
    -0.80
    illoma
    -0.80
    Nested
    -0.78
     COV
    -0.78
    POSITIVE LOGITS
    '}
    0.78
     Preußen
    0.77
     Gastgeber
    0.71
    XXXXXXXX
    0.71
    alline
    0.70
    Nguy
    0.69
    リニューアル
    0.69
    🪬
    0.69
    "};
    0.69
    hundred
    0.69
    Activations Density 0.012%

    No Known Activations