© 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. 44210
    Prev
    Next
    INDEX
    Explanations

    facilitates, normalizes, or depicts

    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
    ت
    1.39
    만을
    1.32
    ي
    1.27
     chlorinated
    1.27
    要知道
    1.23
    цам
    1.22
    ны
    1.21
    ными
    1.20
     обеспечи
    1.19
     elucid
    1.19
    POSITIVE LOGITS
    ch
    1.45
    ro
    1.22
    いない
    1.07
    b
    1.06
    ge
    1.05
    hockey
    1.05
    いる
    1.02
    uo
    1.00
     Usted
    0.99
    ittä
    0.97
    Activations Density 0.198%

    No Known Activations