© 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. 41-GEMMASCOPE-2-RES-262K
    7. 31465
    Prev
    Next
    INDEX
    Explanations

    google

    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
    レル
    0.41
    ೊಂಡ
    0.41
    ଂ
    0.39
    .${
    0.38
     thermally
    0.36
    閾
    0.36
     lump
    0.36
    riages
    0.35
    THEOREM
    0.35
    ⿺
    0.35
    POSITIVE LOGITS
     goog
    2.44
     google
    2.38
     Goog
    2.31
     Google
    2.22
    google
    2.13
    Google
    2.08
     गूगल
    1.93
     গুগল
    1.91
     گوگل
    1.91
    goog
    1.77
    Activations Density 0.000%

    No Known Activations