© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 477
    Prev
    Next
    INDEX
    Explanations

    two parts: Encoder, Decoder

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    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
    ន្ថ
    0.67
    ឡិច
    0.63
     simonsen
    0.60
    繁忙時間服務
    0.59
    <unused1053>
    0.59
    َم
    0.57
    <unused153>
    0.57
    َد
    0.56
    DEBUGFS
    0.56
    arranty
    0.55
    POSITIVE LOGITS
     Statements
    0.59
     Unit
    0.58
     Input
    0.57
     Глав
    0.57
     Structure
    0.55
     Reporter
    0.55
     Biblioteca
    0.55
     Declaration
    0.55
    一个
    0.54
     Building
    0.53
    Activations Density 0.008%

    No Known Activations