© 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. 53-GEMMASCOPE-2-RES-262K
    7. 48498
    Prev
    Next
    INDEX
    Explanations

    reaching or exceeding limits

    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_53_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
    访
    0.43
     radius
    0.40
    icientes
    0.39
     radii
    0.39
     Follow
    0.37
     الصح
    0.37
     rn
    0.35
    }{*}{
    0.35
    肦
    0.35
     able
    0.34
    POSITIVE LOGITS
     exceeded
    2.39
     exceed
    2.34
     exceeding
    2.30
     exceeds
    2.20
     surpassed
    2.14
     surpassing
    2.13
     dépasse
    2.13
     dépass
    2.11
     surpass
    2.06
     превы
    2.06
    Activations Density 0.030%

    No Known Activations