© 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. 10299
    Prev
    Next
    INDEX
    Explanations

    various definitions and compositions

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

    The neuron fires on numeric or identifier‐style tokens (e.g. version numbers, license numbers, DOIs, and other structured numeric/document IDs).

    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
    erweise
    0.79
    en
    0.78
    Suggestion
    0.72
     thesis
    0.71
    Cart
    0.68
    ין
    0.66
    kampf
    0.65
    ardino
    0.64
    র্শ
    0.61
    ज
    0.61
    POSITIVE LOGITS
    agory
    0.89
     paralys
    0.84
    あった
    0.81
    いました
    0.79
     resetCounters
    0.79
    écut
    0.78
     évén
    0.77
     посмотре
    0.77
    lijke
    0.77
    を表示
    0.76
    Activations Density 0.001%

    No Known Activations