© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49621
    Prev
    Next
    INDEX
    Explanations

    in the event of

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

    The neuron activates on numeric tokens, i.e. 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_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
    かって
    -0.82
     Thriller
    -0.79
     Buddhists
    -0.75
     Philadel
    -0.75
     convinces
    -0.74
    異なります
    -0.72
     stater
    -0.72
    ula
    -0.72
    这条
    -0.71
     aban
    -0.71
    POSITIVE LOGITS
     event
    5.97
    event
    4.75
     Event
    3.42
    EVENT
    3.33
    Event
    3.25
     EVENT
    3.22
     evento
    3.08
    イベント
    2.73
     events
    2.56
    getEvent
    2.28
    Activations Density 0.051%

    No Known Activations