© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20013
    Prev
    Next
    INDEX
    Explanations

    C/C++ headers and compiler flags

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

    The neuron is picking out low‐level programming tokens such as standard header names (e.g. “stddef”, “cdefs”, “defs”), file-encoding markers (e.g. “fenc”), and compiler/error flags like “error.”

    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
     from
    -1.93
    u
    -1.91
     the
    -1.58
     called
    -1.55
     our
    -1.55
     it
    -1.52
     sebab
    -1.52
     cantora
    -1.48
     touted
    -1.48
     this
    -1.47
    POSITIVE LOGITS
    4
    1.79
    ем
    1.65
    厹
    1.58
    emptyList
    1.55
     occa
    1.53
    怎么说
    1.53
    ogia
    1.53
    6
    1.53
     เสื้อ
    1.52
     occas
    1.52
    Activations Density 0.001%

    No Known Activations