© 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. 13916
    Prev
    Next
    INDEX
    Explanations

    Objective-C imports and class names

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

    The neuron is specifically detecting import/include directives (e.g. the quoted header filenames) in source code.

    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
    s
    -1.71
    o
    -1.59
     Those
    -1.56
    Ꮸ
    -1.52
    🏨
    -1.45
    Sagittarius
    -1.45
    恶魔
    -1.45
    “
    -1.39
     edile
    -1.38
     gezet
    -1.37
    POSITIVE LOGITS
     of
    2.19
     we
    1.79
    ctico
    1.77
     semua
    1.73
    other
    1.72
     you
    1.66
     they
    1.65
    ੨
    1.65
     enfati
    1.62
     Pristup
    1.59
    Activations Density 0.005%

    No Known Activations