© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 55793
    Prev
    Next
    INDEX
    Explanations

    code snippets and links

    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_65k_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
     equivalent
    0.42
     corresponding
    0.38
     माम
    0.37
    ,.
    0.36
    ्रय
    0.36
     quickly
    0.36
     ó
    0.36
    ारात
    0.36
     lessening
    0.35
     immovable
    0.35
    POSITIVE LOGITS
     quét
    0.39
    ("",
    0.38
    HANG
    0.38
    "("
    0.38
    同學
    0.37
     πάν
    0.37
    "[
    0.37
    ."[
    0.37
    ჷ
    0.37
    ھیں
    0.36
    Activations Density 0.064%

    No Known Activations