© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 249474
    Prev
    Next
    INDEX
    Explanations

    Swiss side or born life

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tov
    0.57
    ണേ
    0.52
    ノ
    0.50
     tested
    0.47
    Ꮲ
    0.47
    ورت
    0.46
    ۆر
    0.46
     garantie
    0.46
     quirk
    0.45
     Joanne
    0.45
    POSITIVE LOGITS
     بالنسبة
    0.48
      
    0.45
    ঙ
    0.44
     পশু
    0.43
     없이
    0.41
    v
    0.41
    ng
    0.40
    ↵↵
    0.40
     축
    0.40
     Relative
    0.40
    Activations Density 0.001%

    No Known Activations