© 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. 14006
    Prev
    Next
    INDEX
    Explanations

    code snippet separators

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

    The neuron fires strongly on Dewey‐style decimal classification numbers (the three‐digit codes with decimals).

    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
     vidéos
    0.79
     sommes
    0.75
    ementara
    0.75
     moteurs
    0.74
    囪
    0.73
    êtres
    0.71
     prochains
    0.71
    IPLE
    0.71
    Airplane
    0.71
     quelcon
    0.71
    POSITIVE LOGITS
     âmbito
    0.83
    บุ
    0.81
     mód
    0.78
     உப
    0.76
     diferenci
    0.76
     ทาง
    0.75
     chronic
    0.75
     ฝ
    0.72
     Fawcett
    0.72
     была
    0.72
    Activations Density 0.001%

    No Known Activations