© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35061
    Prev
    Next
    INDEX
    Explanations

    list items with numbers

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

    This neuron activates on numeric tokens (multi-digit 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
    cún
    -1.02
     towards
    -0.96
    øre
    -0.94
     konusunda
    -0.93
     eventually
    -0.92
     olması
    -0.92
    DrawerLayout
    -0.90
     بیشتری
    -0.86
     إذا
    -0.85
     Johnny
    -0.85
    POSITIVE LOGITS
     chante
    0.96
     ruine
    0.89
     compter
    0.87
    simile
    0.83
    dzie
    0.82
     McIntyre
    0.82
     nutz
    0.81
     ListItem
    0.81
    practices
    0.79
     sü
    0.79
    Activations Density 0.002%

    No Known Activations