© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 124737
    Prev
    Next
    INDEX
    Explanations

    reaching limits or values

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

    The neuron activates on numeric tokens (digits and numeric expressions) 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
     \
    -2.22
    you
    -1.75
     it
    -1.71
     []:
    -1.67
    being
    -1.59
    9
    -1.57
    bers
    -1.56
    no
    -1.55
    }\
    -1.52
    ://$
    -1.51
    POSITIVE LOGITS
     ganzes
    1.82
     besonderes
    1.65
     a
    1.57
     exercer
    1.50
     precin
    1.47
     hitherto
    1.44
     unprecedented
    1.44
     possiamo
    1.42
    後記
    1.41
     antiguos
    1.41
    Activations Density 0.025%

    No Known Activations