© 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-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 30653
    Prev
    Next
    INDEX
    Explanations

    left parenthesis

    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
    ak
    1.44
     funz
    1.37
    い
    1.37
     deswegen
    1.34
     swabs
    1.33
    いっぱい
    1.29
    满满
    1.29
     më
    1.28
    اویز
    1.27
     squats
    1.25
    POSITIVE LOGITS
    Д
    1.57
    gehend
    1.43
    вают
    1.30
    នូវ
    1.26
    Исход
    1.26
    են
    1.25
    Favorite
    1.25
    Примеча
    1.25
    К
    1.23
     Redox
    1.20
    Activations Density 0.001%

    No Known Activations