© 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. 2279
    Prev
    Next
    INDEX
    Explanations

    Motion Picture

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

    The neuron is detecting numeric tokens (sequences of digits, often the numeric IDs or decimal segments in URLs).

    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
     സൂര്യ
    0.65
     しかし
    0.63
     本当
    0.60
    AppBsky
    0.60
     紫
    0.59
     Skyrim
    0.59
     popolazione
    0.55
     Nhưng
    0.55
    ♤
    0.55
     ギフト
    0.55
    POSITIVE LOGITS
     and
    0.48
     adjoining
    0.48
    unc
    0.47
     equivalent
    0.46
     as
    0.45
    copy
    0.45
     over
    0.45
     out
    0.44
     on
    0.42
     inter
    0.42
    Activations Density 0.010%

    No Known Activations