© 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. 24-GEMMASCOPE-2-RES-262K
    7. 9477
    Prev
    Next
    INDEX
    Explanations

    that followed by a clause

    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_24_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
     bereavement
    0.46
     prostit
    0.40
    ва
    0.38
    $.
    0.38
    РЕ
    0.36
    ваме
    0.34
    AntiForgery
    0.34
     borde
    0.34
    恐怕
    0.34
    꽤
    0.34
    POSITIVE LOGITS
    it
    0.52
     তারা
    0.52
     ஒவ்வொரு
    0.51
     প্রতিটি
    0.51
    there
    0.50
    すべての
    0.50
     setiap
    0.48
     it
    0.47
     Every
    0.46
     प्रत्येक
    0.45
    Activations Density 0.013%

    No Known Activations