© 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. 10-GEMMASCOPE-RES-131K
    7. 86931
    Prev
    Next
    INDEX
    Explanations

    symbols and code delimiters

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

    The neuron fires on numeric tokens (digits and numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    \
    -3.08
    ].
    -2.61
     FOR
    -2.52
    ."
    -2.34
     –
    -2.31
     t
    -2.30
    鋮
    -2.25
     ?
    -2.20
     z
    -2.19
     {
    -2.17
    POSITIVE LOGITS
    jų
    2.56
    赑
    2.55
     też
    2.52
    t
    2.52
    a
    2.50
     работал
    2.36
    ðsíða
    2.31
    eſt
    2.30
     itſelf
    2.30
    龗
    2.22
    Activations Density 0.002%

    No Known Activations