© 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. 45485
    Prev
    Next
    INDEX
    Explanations

    lists and numbers in various scripts

    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
     brisk
    1.33
    ла
    1.30
    ுக்கு
    1.27
     plen
    1.27
     FODC
    1.24
    h
    1.23
     Prist
    1.23
     Lampard
    1.22
     Phan
    1.21
    ませんでした
    1.21
    POSITIVE LOGITS
    Л
    1.48
    osaic
    1.30
    কার
    1.27
     silam
    1.27
     ак
    1.25
     सामाजिक
    1.22
     তারিখে
    1.20
     ан
    1.19
    स
    1.19
     πολι
    1.18
    Activations Density 0.055%

    No Known Activations