© 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. 101264
    Prev
    Next
    INDEX
    Explanations

    memmove, probiotic, dissipative

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

    programming code comments and documentation headers.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron detects numeric identifiers and version‐style tokens (e.g. CWE numbers, test case numbers, or digits embedded in code/file names).

    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
     this
    -2.16
    ׇ
    -1.73
     here
    -1.65
     you
    -1.59
     этой
    -1.49
     my
    -1.48
     çünkü
    -1.47
     miércoles
    -1.45
    ἵ
    -1.45
    ੨
    -1.44
    POSITIVE LOGITS
     but
    2.48
    .
    1.61
    During
    1.57
    However
    1.56
     mencionó
    1.41
    cookieParser
    1.41
     грамм
    1.39
    Although
    1.39
    閉店
    1.39
    кет
    1.38
    Activations Density 0.019%

    No Known Activations