© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 57612
    Prev
    Next
    INDEX
    Explanations

    robotics, optics, analytics, economics, genetics

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

    fields or disciplines like "robotics," "optics," and "economics" in academic or technical contexts.

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

    The neuron detects single-word technical or academic field names (e.g. “robotics,” “Optics,” “analytics,” “economics”).

    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
     was
    -2.86
     sanno
    -2.45
    t
    -2.45
    2
    -2.45
     perched
    -2.41
     alluded
    -2.33
    voyez
    -2.31
    ቼ
    -2.30
     slated
    -2.28
     emporio
    -2.22
    POSITIVE LOGITS
    .
    3.20
     entscheid
    2.69
    裢
    2.64
    忖
    2.55
     szükség
    2.48
     серебри
    2.44
     оранже
    2.42
     ярко
    2.33
    痺
    2.33
    ffc
    2.31
    Activations Density 0.050%

    No Known Activations