© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 28351
    Prev
    Next
    INDEX
    Explanations

    mathematical tricks and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stenosis
    0.43
    govt
    0.42
     blockage
    0.41
    اردوشاعری
    0.39
    ˹
    0.39
    Enqueue
    0.39
    ⑰
    0.38
    %%%%%%%%%%%%%%%%
    0.38
    द्वानी
    0.38
     governmental
    0.37
    POSITIVE LOGITS
    rius
    0.42
     (.)
    0.40
     dinámica
    0.40
    ",
    0.39
     (),
    0.38
    iii
    0.38
     teorie
    0.37
     $("
    0.37
     ("",
    0.37
     Windows
    0.37
    Activations Density 0.000%

    No Known Activations