© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 965
    Prev
    Next
    INDEX
    Explanations

    option 1

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

    This neuron selectively responds to standalone numeral tokens used as list or question/item numbers.

    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_24_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
    0.65
    1
    0.63
    9
    0.61
    2
    0.57
    5
    0.55
    4
    0.55
    3
    0.54
    8
    0.53
    7
    0.53
     the
    0.52
    POSITIVE LOGITS
    ：（
    0.58
    ፦
    0.54
     থাকিত
    0.54
    了他的
    0.52
     دماغ
    0.52
     updateConfirm
    0.51
     :"
    0.51
    ulsions
    0.50
     పుష్
    0.50
     adjoining
    0.50
    Activations Density 0.017%

    No Known Activations