© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 7336
    Prev
    Next
    INDEX
    Explanations

    loop counter `i` increments

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

    The neuron selectively activates on numeric tokens and number‐like expressions (e.g. years, measurements, IDs, quantities).

    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
    ;</
    0.68
    ளையும்
    0.65
     ?”
    0.64
    ()?;
    0.61
     विभक्ति
    0.61
    ()?
    0.61
     ||
    0.61
     بیشتر
    0.60
    ᵗ
    0.60
    ளிலும்
    0.59
    POSITIVE LOGITS
    ++)
    0.62
     ++)
    0.61
    ++]
    0.55
     '/')
    0.55
    ++){
    0.53
    --)
    0.52
    =',
    0.52
    \%)
    0.52
    ++,
    0.51
     खेळा
    0.51
    Activations Density 0.009%

    No Known Activations