© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 3306
    Prev
    Next
    INDEX
    Explanations

    exhaust system components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ellä
    1.12
    可以
    1.09
    ítmény
    1.05
    すすめ
    1.01
    蒌
    0.98
    には
    0.97
    完全
    0.97
    值为
    0.97
    就是
    0.96
    平板
    0.96
    POSITIVE LOGITS
     piqu
    1.30
    ください
    1.25
     snatch
    1.21
    ur
    1.20
     earbuds
    1.12
     realizados
    1.09
    ्स
    1.09
    sch
    1.09
     echoed
    1.09
     desist
    1.07
    Activations Density 0.000%

    No Known Activations