© 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. 128622
    Prev
    Next
    INDEX
    Explanations

    programming keywords and types

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

    The neuron activates on programming data‐type or system‐type identifiers (e.g. BYTE, BSTR, unichar, UINT, HKEY, NSUInteger).

    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
    (
    -2.09
    síða
    -1.82
    -
    -1.64
    ”
    -1.59
    ph
    -1.59
     хотела
    -1.53
    ,”
    -1.53
    l
    -1.48
    dáms
    -1.48
    ib
    -1.47
    POSITIVE LOGITS
     and
    1.83
    焄
    1.67
    ければ
    1.66
    corpions
    1.63
     admitir
    1.56
     ajustar
    1.53
    apatalk
    1.53
    /")
    1.52
    []
    1.52
    ！"
    1.49
    Activations Density 0.005%

    No Known Activations