© 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. 85081
    Prev
    Next
    INDEX
    Explanations

    Date, swap, fitness

    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
    date
    0.44
    ლებიც
    0.44
    日期
    0.42
    DATE
    0.40
    Przeczytaj
    0.40
    佹
    0.40
    rocery
    0.39
    enaire
    0.39
    চীনের
    0.38
    📆
    0.38
    POSITIVE LOGITS
     Highlights
    0.43
     SwitchCompat
    0.40
                             
    0.39
     Played
    0.39
     KK
    0.38
     Scalars
    0.38
     Dism
    0.38
     ဆ
    0.38
     maximized
    0.37
     Gains
    0.37
    Activations Density 0.000%

    No Known Activations