© 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. 209966
    Prev
    Next
    INDEX
    Explanations

    image capture and loading

    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
     androidx
    0.40
     pushed
    0.39
    荕
    0.39
     கல்
    0.38
     coupons
    0.38
    ロップ
    0.38
    군은
    0.38
     impressed
    0.38
     canceled
    0.38
    岌
    0.38
    POSITIVE LOGITS
    Button
    0.41
     weather
    0.39
    apping
    0.38
    yst
    0.38
     ulo
    0.38
     Button
    0.37
    antai
    0.36
     Tent
    0.36
    iyas
    0.36
    ats
    0.36
    Activations Density 0.001%

    No Known Activations