© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 5877
    Prev
    Next
    INDEX
    Explanations

    rates and quantities

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

    The neuron fires on precise numeric measurements—especially floating‐point values—like detailed temperature or specification 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
    zyloxy
    0.65
     vertebrae
    0.59
     phạt
    0.59
     unnecessary
    0.58
    డ
    0.55
    )$;
    0.55
    ivam
    0.55
    frame
    0.55
     đáng
    0.55
     frame
    0.54
    POSITIVE LOGITS
    振兴
    0.67
     aon
    0.65
     avanzada
    0.64
     continuer
    0.64
    诽
    0.63
     ilyen
    0.62
     bakan
    0.61
     avanz
    0.61
     ausp
    0.61
     Tsuen
    0.61
    Activations Density 0.000%

    No Known Activations