© 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. 50469
    Prev
    Next
    INDEX
    Explanations

    programming code and libraries

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

    The neuron strongly activates on sequences of digits (numeric literals).

    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
     path
    -0.77
    path
    -0.73
    biť
    -0.69
     ormai
    -0.67
    enter
    -0.67
    抱
    -0.67
    endam
    -0.66
    Keeper
    -0.66
    SRS
    -0.66
     XXXI
    -0.65
    POSITIVE LOGITS
    henko
    0.74
    чества
    0.68
    шенко
    0.66
     LEFT
    0.64
     Sql
    0.63
     servers
    0.63
    omene
    0.62
    Ufficio
    0.62
    банк
    0.62
    grayscale
    0.62
    Activations Density 0.138%

    No Known Activations