© 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. 34-GEMMASCOPE-RES-131K
    4. 102986
    Prev
    Next
    INDEX
    Explanations

    /** or Union or Link or Q"}, "in writing"

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

    This neuron fires on numeric tokens (i.e. sequences of digits) 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_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
     francia
    -1.09
     musul
    -0.95
    RAT
    -0.90
    barn
    -0.88
    **********
    -0.85
    🤯
    -0.84
    моло
    -0.83
    creme
    -0.83
     kapag
    -0.83
    🍝
    -0.82
    POSITIVE LOGITS
     osoby
    1.05
    Kommentar
    0.93
     attacco
    0.92
     fidanz
    0.91
     viviendas
    0.88
     отметил
    0.87
     enchufe
    0.86
     richiesto
    0.83
     assoluto
    0.82
     увеличить
    0.81
    Activations Density 0.000%

    No Known Activations