© 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. 116772
    Prev
    Next
    INDEX
    Explanations

    copyright statements and licenses

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

    The neuron is chiefly triggered by numeric tokens (stand-alone digit sequences).

    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
     SG
    -0.67
    zesi
    -0.65
    óis
    -0.65
     Pote
    -0.64
     entorno
    -0.62
     ack
    -0.61
    Coordination
    -0.61
     traceable
    -0.60
    褚
    -0.60
    imientos
    -0.60
    POSITIVE LOGITS
     Technol
    0.73
     принце
    0.73
    机械
    0.69
     Aad
    0.68
    Dialect
    0.68
    infix
    0.68
    Bitpie
    0.67
    Uploader
    0.67
    Pj
    0.66
     Whitby
    0.66
    Activations Density 0.075%

    No Known Activations