© 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-65K
    7. 3338
    Prev
    Next
    INDEX
    Explanations

    introductions to explanations

    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_65k_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
    บ้าง
    0.46
     অথবা
    0.46
    অর্থাৎ
    0.45
    のではなく
    0.44
    =?,
    0.44
     अथवा
    0.44
    instead
    0.44
    ziej
    0.42
    ？」
    0.42
    Glor
    0.41
    POSITIVE LOGITS
     особенно
    0.69
     özellikle
    0.69
     😍
    0.68
     especially
    0.65
    !
    0.64
     thanks
    0.64
     underrated
    0.64
    尤其是
    0.63
    собенно
    0.62
    특히
    0.61
    Activations Density 0.290%

    No Known Activations