© 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. 19408
    Prev
    Next
    INDEX
    Explanations

    The dean's ... Tucking the adverb

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

    The neuron fires on numeric tokens—especially floating‐point or decimal numbers—in the text.

    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
     แต่
    -1.56
     ถ้า
    -1.52
     และ
    -1.46
    dte
    -1.44
     gustar
    -1.40
    ARIOS
    -1.38
    ˂
    -1.36
    levis
    -1.34
     The
    -1.27
     dieser
    -1.26
    POSITIVE LOGITS
     robić
    1.66
     subsequently
    1.61
     навіть
    1.54
     even
    1.47
    _
    1.40
     beschränkt
    1.38
     subsequent
    1.33
     what
    1.29
     INCORPOR
    1.26
     specially
    1.25
    Activations Density 0.020%

    No Known Activations