© 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. 65143
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

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

    The neuron fires on numeric tokens (digits, numbers, and numeric constants).

    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
    The
    -3.00
    1
    -2.64
    要在
    -2.36
    焄
    -2.34
    s
    -2.34
     каким
    -2.33
     throng
    -2.33
     cliquer
    -2.30
    But
    -2.22
     femeninos
    -2.09
    POSITIVE LOGITS
    甞
    2.98
    ?”
    2.66
    栳
    2.58
    ')
    2.50
    z
    2.41
     berdua
    2.38
    荦
    2.38
    ,”
    2.28
    ghalaya
    2.25
    鬭
    2.25
    Activations Density 0.009%

    No Known Activations