© 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. 120827
    Prev
    Next
    INDEX
    Explanations

    operating systems or popular places

    np_acts-logits-general · gemini-2.5-flash-lite

    West Side Story movie accent

    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
    u
    0.46
    rb
    0.45
     pagal
    0.45
     rb
    0.45
     RB
    0.43
    as
    0.43
     tailor
    0.42
     comfortable
    0.42
     slightly
    0.42
     cos
    0.41
    POSITIVE LOGITS
     крепо
    0.48
     meriye
    0.48
    Firefox
    0.47
     укреп
    0.46
    腧
    0.46
     እንቅስቃሴ
    0.46
    ফটেন্যান্ট
    0.46
     केंद
    0.45
    ቀ
    0.45
     beslut
    0.44
    Activations Density 0.001%

    No Known Activations