© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10633
    Prev
    Next
    INDEX
    Explanations

    sequence followed by punctuation or letter

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

    This neuron activates on numeric tokens and number-like expressions (e.g. digits, multi‐digit figures, or decimals).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    5
    0.65
    8
    0.64
    ８
    0.61
    ５
    0.61
    6
    0.60
    7
    0.59
    9
    0.59
    ７
    0.59
    ６
    0.58
    ３
    0.52
    POSITIVE LOGITS
     former
    0.49
     individuals
    0.47
     stations
    0.47
     personnes
    0.47
    imeters
    0.47
    ktion
    0.46
    ujourd
    0.46
     rectangles
    0.46
    ­
    0.45
     residential
    0.45
    Activations Density 0.072%

    No Known Activations