© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 75441
    Prev
    Next
    INDEX
    Explanations

    historical and current events

    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_31_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
    ناط
    0.46
    riched
    0.46
    ின்றன
    0.45
    侈
    0.45
    طاء
    0.44
    வ்வேறு
    0.44
    Dispatcher
    0.44
    習慣
    0.44
    ства
    0.44
    SrvGroup
    0.43
    POSITIVE LOGITS
     ป
    0.50
     Ди
    0.47
     crosses
    0.47
     혹은
    0.46
     ок
    0.45
     fx
    0.44
     हु
    0.44
     detects
    0.44
     Ф
    0.44
     У
    0.43
    Activations Density 0.000%

    No Known Activations