© 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. 204499
    Prev
    Next
    INDEX
    Explanations

    yourself honest

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

    movie meets, cosmic horror, offer letter

    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
    ک
    0.54
    ړئ
    0.53
    operasi
    0.53
    व्यक्ति
    0.52
     centrifugation
    0.52
     कामकाज
    0.52
    وای
    0.51
    azität
    0.51
    టన
    0.50
    ektion
    0.49
    POSITIVE LOGITS
    算了
    0.47
    غير
    0.45
    .°
    0.43
    }&
    0.42
     gerente
    0.41
    通道
    0.40
    ír
    0.39
    гром
    0.39
    law
    0.38
     бро
    0.38
    Activations Density 0.000%

    No Known Activations