© 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. 31-GEMMASCOPE-2-RES-16K
    7. 5479
    Prev
    Next
    INDEX
    Explanations

    tables, lists, and comparisons

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

    This neuron detects standalone numeric tokens or numeric measurements (including table/figure numbers and decimal values).

    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
     feces
    0.56
     prenatal
    0.53
     yil
    0.53
     college
    0.52
     req
    0.51
     brit
    0.51
     embryo
    0.51
    </tfoot>
    0.50
     chatting
    0.49
     fragmented
    0.49
    POSITIVE LOGITS
    ccccc
    1.33
    lllll
    1.26
    cccc
    1.23
    llll
    1.20
    ccc
    1.17
    llllll
    1.16
    cccccc
    1.13
    lll
    1.09
    lcc
    1.05
    lccc
    1.04
    Activations Density 0.010%

    No Known Activations