© 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. 8984
    Prev
    Next
    INDEX
    Explanations

    want to express desire

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

    want to

    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
    ك
    0.64
    ق
    0.62
    ف
    0.61
    with
    0.57
    ک
    0.55
    ב
    0.52
    یک
    0.50
    ج
    0.50
    ب
    0.49
    Від
    0.49
    POSITIVE LOGITS
    :
    0.43
    t
    0.42
     спасибо
    0.42
    ри
    0.40
    ль
    0.40
     Анто
    0.40
    erer
    0.40
     WE
    0.40
    erne
    0.40
    esha
    0.39
    Activations Density 0.072%

    No Known Activations