© 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. 73608
    Prev
    Next
    INDEX
    Explanations

    closing punctuation after said

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

    The neuron strongly activates on numeric tokens (digits and number strings) in the text, i.e. it detects occurrences of numbers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     their
    -1.20
     even
    -1.10
     by
    -1.10
     just
    -1.08
     चीज़ों
    -1.05
     lantaran
    -1.00
    шат
    -0.98
     intér
    -0.97
    xmlhttp
    -0.97
    PENDAHULUAN
    -0.97
    POSITIVE LOGITS
    kách
    1.16
     administrativos
    1.13
    Amical
    1.09
     スリーブ
    1.07
    diğ
    1.07
    缡
    1.02
     educativas
    1.02
     factoring
    1.00
     oust
    1.00
     educativos
    0.99
    Activations Density 0.004%

    No Known Activations