© 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. 19278
    Prev
    Next
    INDEX
    Explanations

    mathematical or code definition cases

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

    The neuron activates on numeric tokens (including integers, decimals, and other digit‐based strings).

    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
    Ayrıca
    -1.80
    zkod
    -1.72
    olkien
    -1.68
    任何
    -1.66
    tadiene
    -1.59
     JUGA
    -1.59
     рекомендую
    -1.56
    糌
    -1.55
    şem
    -1.54
     <=",
    -1.53
    POSITIVE LOGITS
     is
    2.55
     these
    1.98
     was
    1.55
    いただける
    1.51
     should
    1.45
    should
    1.45
     '
    1.42
     Should
    1.41
     .
    1.38
     teď
    1.36
    Activations Density 0.001%

    No Known Activations