© 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. 169518
    Prev
    Next
    INDEX
    Explanations

    steps and conditions

    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
    TABLE
    0.42
     sharp
    0.41
     seh
    0.40
    <table>
    0.40
     mn
    0.38
    既然
    0.38
    シンプルな
    0.36
    :\\
    0.36
    figure
    0.36
     brands
    0.36
    POSITIVE LOGITS
    oplayer
    0.43
    aduct
    0.40
    PERATURE
    0.40
     bezoek
    0.40
     방문
    0.40
     voork
    0.39
    wad
    0.39
     стаўкі
    0.39
    ڈین
    0.38
    iftoire
    0.38
    Activations Density 0.380%

    No Known Activations