© 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. 199879
    Prev
    Next
    INDEX
    Explanations

    look like; still something; you can

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

    query library

    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
    ,
    0.50
    ństwa
    0.45
    ным
    0.45
     divulge
    0.44
    ;
    0.44
     indefinitely
    0.44
    ność
    0.43
    坐在
    0.42
    лек
    0.42
     Faker
    0.42
    POSITIVE LOGITS
     হ্যাঁ
    0.46
    arbe
    0.46
     ਕੁ
    0.45
     用户
    0.44
     Besonder
    0.44
    輥
    0.44
    獷
    0.44
    ลล์
    0.43
     lungs
    0.43
    urbs
    0.43
    Activations Density 0.001%

    No Known Activations