© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 111804
    Prev
    Next
    INDEX
    Explanations

    slick and deals

    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
     jiwa
    0.38
     flanges
    0.38
     Saving
    0.38
    Saving
    0.38
     saving
    0.37
     nomads
    0.37
    று
    0.37
    狯
    0.37
     BOUND
    0.36
    Ó
    0.36
    POSITIVE LOGITS
     Ritter
    0.40
    центри
    0.39
     প্লে
    0.37
    iph
    0.37
    pixel
    0.36
    issimi
    0.36
    
    0.36
     Vert
    0.35
    bilder
    0.35
     зда
    0.35
    Activations Density 0.000%

    No Known Activations