© 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-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 224640
    Prev
    Next
    INDEX
    Explanations

    shapes, routes, and data sources

    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_40_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
    --’
    0.44
    首席
    0.39
    礽
    0.37
    ษ
    0.36
    只需要
    0.35
     ظل
    0.34
    Helix
    0.34
     Prelude
    0.34
    鱻
    0.34
    IGHT
    0.33
    POSITIVE LOGITS
    immers
    0.44
    heiser
    0.41
     outbound
    0.41
    ifié
    0.40
     consignment
    0.39
    ブリッド
    0.38
    imb
    0.38
    qy
    0.38
    obod
    0.37
    specification
    0.37
    Activations Density 0.000%

    No Known Activations