© 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. 59876
    Prev
    Next
    INDEX
    Explanations

    Formula selling, asset, event

    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
     passionate
    0.45
     Sabb
    0.39
    exec
    0.38
     Exec
    0.37
    Hor
    0.36
    apath
    0.36
    robe
    0.36
     周
    0.35
     நடந்து
    0.35
    discipl
    0.35
    POSITIVE LOGITS
     کہانی
    0.39
    ekeeping
    0.38
    ூக
    0.37
    遙
    0.37
     eli
    0.37
    برد
    0.37
    ifend
    0.37
     oid
    0.36
    postId
    0.36
    îtier
    0.36
    Activations Density 0.001%

    No Known Activations