© 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. 1560
    Prev
    Next
    INDEX
    Explanations

    initials and punctuation

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

    This neuron detects numeric tokens, especially numbers with decimal points (e.g. “114.5,” “105.5,” “95.5”).

    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
    lético
    -1.72
    涐
    -1.67
    槼
    -1.67
     churrasco
    -1.62
     ajuta
    -1.61
     galinha
    -1.59
     bekan
    -1.59
    过来了
    -1.57
     connaît
    -1.56
    实话
    -1.53
    POSITIVE LOGITS
     or
    1.55
     to
    1.45
    ’
    1.41
     tillegg
    1.38
     После
    1.33
     некоторые
    1.32
    、
    1.31
     主要
    1.29
     основ
    1.26
    </h4>
    1.20
    Activations Density 0.037%

    No Known Activations