© 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. 79183
    Prev
    Next
    INDEX
    Explanations

    HTML/code syntax and structure

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

    The neuron strongly activates on code‐style constants, directives, and other uppercase or symbol‐heavy tokens (e.g. PDO::PARAM_INT, return, “---”, version numbers, all‐caps identifiers).

    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
    weit
    -0.83
     seawater
    -0.78
     insects
    -0.73
     insurgency
    -0.70
    Insect
    -0.70
     macchina
    -0.70
     Insect
    -0.69
    lielmo
    -0.68
     ymax
    -0.68
     tanaman
    -0.68
    POSITIVE LOGITS
     沈
    0.76
    IRA
    0.69
    träglich
    0.67
     Alla
    0.64
     Than
    0.64
     Cep
    0.60
     Browning
    0.60
    ﺳ
    0.59
     Selma
    0.59
    lya
    0.59
    Activations Density 0.077%

    No Known Activations