© 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. 5833
    Prev
    Next
    INDEX
    Explanations

    levels of

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

    The neuron detects occurrences of the word “level” (especially “levels”).

    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
    ных
    1.25
    ar
    1.13
    ة
    1.03
     чрезвы
    1.02
     листь
    1.00
     primeros
    0.98
     كتبت
    0.97
     duet
    0.96
     portada
    0.96
     фотографи
    0.93
    POSITIVE LOGITS
     vya
    1.13
    巅
    1.13
    レベル
    1.03
    getLevel
    1.03
    ہ
    1.03
    兢
    1.01
     sophistication
    0.98
     acetylation
    0.95
    בר
    0.94
     ಮಟ್ಟ
    0.94
    Activations Density 0.009%

    No Known Activations