© 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. 92755
    Prev
    Next
    INDEX
    Explanations

    .m and .h files

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

    This neuron strongly activates on Objective-C source file names and extensions (e.g. “.h” and “.m” tokens).

    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
     Arundel
    -0.75
    -0.72
    AYER
    -0.71
    kaar
    -0.68
    lly
    -0.68
    papers
    -0.68
    吩咐
    -0.67
     toit
    -0.66
    <0x87>
    -0.66
    čes
    -0.64
    POSITIVE LOGITS
     alapján
    0.71
    abito
    0.68
    rifying
    0.65
    خته
    0.65
     Horton
    0.63
    زر
    0.62
    nologia
    0.61
     ギャ
    0.61
    Isra
    0.61
     Ranking
    0.61
    Activations Density 0.063%

    No Known Activations