© 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. 40-GEMMASCOPE-2-RES-262K
    7. 35857
    Prev
    Next
    INDEX
    Explanations

    int and descriptor handles

    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
    蹊
    0.44
    subTest
    0.40
    TryGetValue
    0.39
    蹺
    0.38
    のこ
    0.38
    alaikums
    0.37
     knocking
    0.36
     vur
    0.36
    綽
    0.36
    bedrooms
    0.36
    POSITIVE LOGITS
    Handle
    0.68
     handle
    0.64
     Handle
    0.64
    handle
    0.50
     HANDLE
    0.49
    ハンドル
    0.48
     sockfd
    0.48
     NULL
    0.46
    NULL
    0.46
    Associated
    0.45
    Activations Density 0.009%

    No Known Activations