© 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. 101944
    Prev
    Next
    INDEX
    Explanations

    in the

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

    The main thing this neuron does is detect numeric tokens—especially multi‐digit 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
    よい
    -1.69
    栳
    -1.64
    ⦊
    -1.63
     diyor
    -1.61
    ?&
    -1.60
    枼
    -1.60
     furent
    -1.59
    锃
    -1.58
    ことがあります
    -1.56
    第一时间
    -1.55
    POSITIVE LOGITS
     to
    2.30
     have
    1.98
     since
    1.65
     will
    1.58
     with
    1.55
     without
    1.41
    的
    1.41
    т
    1.41
     的
    1.38
     out
    1.35
    Activations Density 0.073%

    No Known Activations