© 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. 113695
    Prev
    Next
    INDEX
    Explanations

    code compilation and analysis

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

    the word "compile" and related build/compilation terms in programming contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron detects programming or build-related action words—especially “compile,” “build,” and similar terms.

    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
    jenigen
    -2.16
     jejich
    -2.11
     podemos
    -2.11
    嘥
    -2.11
     apenas
    -2.09
    蠵
    -2.08
     erwähnten
    -2.06
     gesuchten
    -2.05
     vollständige
    -2.05
     impetus
    -2.05
    POSITIVE LOGITS
    It
    3.22
    If
    2.97
    You
    2.97
    what
    2.97
    There
    2.80
    because
    2.78
    ments
    2.66
    Unlike
    2.64
    Also
    2.58
    Because
    2.47
    Activations Density 0.057%

    No Known Activations