© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3472
    Prev
    Next
    INDEX
    Explanations

    American biographical

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

    The neuron detects C/C++ (and similar) header‐file include directives (e.g. lines starting with “#include” followed by a “.h” filename in quotes).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    Colonel
    -0.82
     Colonel
    -0.75
    mith
    -0.72
     enak
    -0.72
     Мне
    -0.69
    rika
    -0.68
    amd
    -0.68
    Twice
    -0.68
     medalla
    -0.67
    rative
    -0.67
    POSITIVE LOGITS
    ாய்
    0.85
    café
    0.82
    político
    0.77
    ędziesz
    0.77
     Fuzzy
    0.76
     oliveira
    0.75
    school
    0.74
     INST
    0.73
    говори
    0.72
     :>
    0.72
    Activations Density 0.016%

    No Known Activations