© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7670
    Prev
    Next
    INDEX
    Explanations

    list sorting algorithms

    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/layer_31_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
    rangea
    0.31
    Leod
    0.31
    AppDelegate
    0.30
    auern
    0.30
    Ŏ
    0.30
    યર
    0.30
    acken
    0.30
    seekBar
    0.30
    echolog
    0.29
     இதையடுத்து
    0.29
    POSITIVE LOGITS
     tình
    0.31
     भी
    0.31
     bình
    0.30
     سه
    0.30
     ৫
    0.30
     phẩm
    0.30
     подобных
    0.30
     أي
    0.29
     사랑
    0.29
     라이
    0.29
    Activations Density 0.039%

    No Known Activations