© 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. 127786
    Prev
    Next
    INDEX
    Explanations

    code gens

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

    The neuron is specifically triggered by occurrences of the literal token “code,” especially when it appears as part of filenames, headings, or code‐section labels.

    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
    \
    -1.87
    ’
    -1.69
     or
    -1.61
     etc
    -1.48
     aka
    -1.45
    这也是
    -1.39
     I
    -1.35
    }
    -1.34
     MOST
    -1.34
     casi
    -1.34
    POSITIVE LOGITS
     Inſ
    1.74
    CIÓN
    1.70
     estadounid
    1.63
    ⿵
    1.63
    ệnh
    1.63
     Belakang
    1.62
    Ꮉ
    1.60
     玄関
    1.59
     recibirá
    1.59
    ósito
    1.58
    Activations Density 0.045%

    No Known Activations