© 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. 41-GEMMASCOPE-2-RES-262K
    7. 57456
    Prev
    Next
    INDEX
    Explanations

    modern application

    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_all/layer_41_width_262k_l0_big
    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
    ed
    0.46
     Global
    0.43
    +'
    0.43
     population
    0.41
    Fuel
    0.39
    os
    0.38
    気分
    0.38
    Global
    0.38
     Big
    0.37
     polis
    0.37
    POSITIVE LOGITS
    咅
    0.46
    㑯
    0.43
     unattractive
    0.42
    льнявыя
    0.39
     সঞ্জ
    0.38
     incons
    0.38
     commens
    0.38
    難しい
    0.38
    ノン
    0.38
    
    0.38
    Activations Density 0.000%

    No Known Activations