© 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. 90271
    Prev
    Next
    INDEX
    Explanations

    projects, reviews, place, eating, frame

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

    sanctioned chaos

    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
    ّة
    0.44
     الناتج
    0.41
     disguise
    0.41
     underval
    0.40
     அனைத்தும்
    0.40
    ๋
    0.40
    ீ
    0.40
    یز
    0.40
     цена
    0.40
     لف
    0.40
    POSITIVE LOGITS
    beros
    0.47
    오늘은
    0.44
    বস্ত
    0.43
    Mental
    0.43
    这就是
    0.43
    WebSocket
    0.43
    Aaron
    0.43
    Window
    0.42
     Âu
    0.42
     写
    0.42
    Activations Density 0.001%

    No Known Activations