© 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. 34-GEMMASCOPE-RES-131K
    7. 49963
    Prev
    Next
    INDEX
    Explanations

    numbers and foreign words (like 와, ῥ, चना, Посилання)

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

    The neuron is tuned to detect numeric tokens and number-like sequences (digits, dashes in IDs, version or section 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_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
    𝚜
    -0.72
    Inherited
    -0.72
    Expected
    -0.69
    xically
    -0.69
    Nicole
    -0.68
     Hiller
    -0.66
    控制器
    -0.66
     pomi
    -0.65
     Terrible
    -0.64
    пой
    -0.64
    POSITIVE LOGITS
    kele
    0.77
     magg
    0.75
    ushu
    0.73
    와
    0.71
    ῥ
    0.71
    RETT
    0.68
    ỏng
    0.68
    चना
    0.68
    AndWait
    0.67
    Посилання
    0.66
    Activations Density 0.060%

    No Known Activations