© 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. 135935
    Prev
    Next
    INDEX
    Explanations

    section titles or topic introductions

    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
    이지만
    0.53
    ༞
    0.52
    WaitingTime
    0.51
    一手
    0.51
    जैसे
    0.48
    ก่อน
    0.48
    Jin
    0.48
    AfterTax
    0.48
    Mosaic
    0.48
    只限平日
    0.48
    POSITIVE LOGITS
     it
    0.60
     this
    0.58
     by
    0.52
     Ш
    0.51
     У
    0.51
     Besch
    0.51
     Ба
    0.50
     Berc
    0.50
     На
    0.49
     Ł
    0.48
    Activations Density 0.000%

    No Known Activations