© 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-65K
    7. 379
    Prev
    Next
    INDEX
    Explanations

    real-time information

    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_65k_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
    เวณ
    0.37
     venturing
    0.37
    沬
    0.36
    ۱۳
    0.36
    Wed
    0.34
     notifier
    0.34
    🤠
    0.34
    jects
    0.34
    otherArchive
    0.34
    Notifier
    0.33
    POSITIVE LOGITS
     pristine
    0.38
     temer
    0.38
     joy
    0.38
    indice
    0.37
     indices
    0.36
    餐廳
    0.36
    ଖ
    0.36
     savo
    0.35
    strftime
    0.34
     πρά
    0.33
    Activations Density 0.061%

    No Known Activations