© 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. 211921
    Prev
    Next
    INDEX
    Explanations

    Wifi, Bluetooth, triangle, time, code

    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
    ุงเทพ
    0.42
    धिकारिक
    0.40
    خدم
    0.39
    সাথে
    0.38
    等你
    0.38
    畀
    0.38
    ژه
    0.38
     Londra
    0.38
     groot
    0.37
     vissza
    0.37
    POSITIVE LOGITS
     వ్యవస్థ
    0.41
    facial
    0.39
    nast
    0.38
    いう
    0.38
    stove
    0.38
     Nast
    0.38
     सहन
    0.38
     stoves
    0.37
     顔
    0.37
    ρίζ
    0.36
    Activations Density 0.000%

    No Known Activations