© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69386
    Prev
    Next
    INDEX
    Explanations

    lambda, spike, diabetics, steroid, males, triangular

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

    articles "the" that precede scientific measurements or data values.

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

    The main thing this neuron does is find numeric measurements (especially decimal and fractional numbers).

    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
     or
    -1.98
     myös
    -1.81
     also
    -1.78
     Usually
    -1.73
     också
    -1.70
     Also
    -1.68
     também
    -1.66
     with
    -1.66
     también
    -1.66
     भी
    -1.61
    POSITIVE LOGITS
    those
    1.57
    particularly
    1.55
    having
    1.52
     '/')
    1.52
    suddenly
    1.48
    partly
    1.47
    increased
    1.45
    recently
    1.44
     mentre
    1.43
    possibly
    1.41
    Activations Density 0.124%

    No Known Activations