© 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. 22-GEMMASCOPE-RES-131K
    7. 130941
    Prev
    Next
    INDEX
    Explanations

    The neuron is specialized in detecting numeric tokens (including integers and decimals) wherever they appear in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    transition words and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     but
    -1.03
     miſ
    -0.85
     primul
    -0.83
    nearly
    -0.82
     kated
    -0.82
     part
    -0.79
    CONT
    -0.78
    Teil
    -0.77
     Teil
    -0.77
    وفق
    -0.77
    POSITIVE LOGITS
    atorium
    0.91
     Erhöhung
    0.84
     offenbar
    0.83
     Frat
    0.83
     with
    0.81
    كد
    0.79
     valley
    0.79
    řen
    0.78
    ža
    0.77
    stk
    0.77
    Activations Density 0.055%

    No Known Activations