© 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. 31-GEMMASCOPE-2-RES-262K
    4. 125870
    Prev
    Next
    INDEX
    Explanations

    impact, reactivation, risk

    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
    _
    0.53
    。
    0.50
     беско
    0.47
    、
    0.47
    してください
    0.46
    ció
    0.46
    和
    0.46
    ##
    0.46
    この
    0.45
    -
    0.44
    POSITIVE LOGITS
    േഷ്
    0.44
     ಏಕೆ
    0.44
     Ayrıca
    0.42
     større
    0.42
     عم
    0.41
     Also
    0.41
     عدة
    0.40
     एरिया
    0.40
    Claims
    0.40
    崤
    0.40
    Activations Density 0.005%

    No Known Activations