© 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. 22-GEMMASCOPE-RES-131K
    7. 104357
    Prev
    Next
    INDEX
    Explanations

    numbers and specific tokens

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

    The neuron fires on tokens that are purely numeric (i.e. standalone 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_22/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
     setIs
    -0.95
    пів
    -0.84
     what
    -0.84
    IZING
    -0.84
     to
    -0.84
     spirituelle
    -0.83
     TextFormField
    -0.83
     its
    -0.82
    uarga
    -0.81
     иннова
    -0.80
    POSITIVE LOGITS
     postulate
    1.02
     浴室
    1.00
     severa
    0.93
     Sugges
    0.93
     アイス
    0.92
    ierter
    0.91
     Generates
    0.90
    hnte
    0.90
     cgi
    0.87
     sprouting
    0.86
    Activations Density 0.011%

    No Known Activations