© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14561
    Prev
    Next
    INDEX
    Explanations

    concepts followed by descriptive words

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

    The neuron flags numeric tokens—especially multi‐digit numbers, decimals, and other explicit numerical references.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     can
    0.91
     are
    0.70
     può
    0.70
     is
    0.70
     may
    0.67
     has
    0.66
     puede
    0.65
    can
    0.64
     adalah
    0.63
    을
    0.63
    POSITIVE LOGITS
     rescheduled
    0.59
    bestroute
    0.57
    但他
    0.55
     ماما
    0.55
     kickoff
    0.54
    開幕
    0.52
    timetable
    0.52
    เขา
    0.51
    他就
    0.51
     председа
    0.51
    Activations Density 0.000%

    No Known Activations