© 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. 2959
    Prev
    Next
    INDEX
    Explanations

    วิธี

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

    This neuron detects enthusiastic, positive descriptive adjectives (often promotional or enticing qualifiers) in non-English (e.g. Vietnamese or Thai) text.

    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
     ("
    0.67
     («
    0.65
     Descartes
    0.65
     (
    0.64
    ；
    0.64
     without
    0.63
     Kullan
    0.63
     [
    0.63
     （
    0.63
     ;
    0.62
    POSITIVE LOGITS
    สุด
    0.80
    มา
    0.80
    มาก
    0.79
     особенностей
    0.79
    มากๆ
    0.78
    แล้ว
    0.78
    จ
    0.77
    แค่
    0.76
    коно
    0.75
    จัด
    0.75
    Activations Density 0.000%

    No Known Activations