© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76868
    Prev
    Next
    INDEX
    Explanations

    ajax jquery angularjs scripts

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

    The neuron activates specifically on sequences of digits—i.e. numeric literals such as version numbers, IDs, URLs with numbers, and other digit 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_34/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
     التجار
    -0.79
     moder
    -0.76
     刺
    -0.75
     الاتحاد
    -0.74
    isler
    -0.72
    ᵉ
    -0.72
    Studies
    -0.71
     戸
    -0.68
     mortgagee
    -0.68
    ziz
    -0.68
    POSITIVE LOGITS
     continual
    0.71
    Fär
    0.69
     Mue
    0.66
    PILE
    0.65
    ılmış
    0.64
     judgements
    0.63
     Compli
    0.63
    oche
    0.62
     continuous
    0.62
    componentWill
    0.61
    Activations Density 0.052%

    No Known Activations