© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 118864
    Prev
    Next
    INDEX
    Explanations

    titles and specific entities

    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
     anise
    0.38
     Oat
    0.37
    
    0.37
     개발
    0.37
    表演
    0.37
     উপদেশ
    0.36
    ='.
    0.36
    pubescens
    0.36
    osk
    0.36
    囿
    0.35
    POSITIVE LOGITS
    точно
    0.38
    ِب
    0.37
    ними
    0.36
    रण
    0.36
    ByMerging
    0.36
     estrell
    0.35
    ····
    0.35
    ----
    0.35
    ຍ
    0.35
    ・・・
    0.34
    Activations Density 0.000%

    No Known Activations