© 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. 41-GEMMASCOPE-2-RES-262K
    7. 5456
    Prev
    Next
    INDEX
    Explanations

    particles moved around verb

    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_all/layer_41_width_262k_l0_big
    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
    ્વ
    0.41
    ว้าง
    0.38
    ղ
    0.38
    ﻢ
    0.37
    笉
    0.37
     designee
    0.36
    黟
    0.36
    ေါ
    0.35
     grandeza
    0.35
    かれる
    0.35
    POSITIVE LOGITS
     up
    0.50
     uptake
    0.46
     Upt
    0.46
     makeup
    0.45
     ups
    0.44
     uphold
    0.44
    upt
    0.43
    ups
    0.43
     breakdown
    0.43
     uph
    0.42
    Activations Density 0.001%

    No Known Activations