© 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. 59549
    Prev
    Next
    INDEX
    Explanations

    LEGO elements

    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
     double
    0.55
    Double
    0.52
     tape
    0.50
    double
    0.49
     Double
    0.49
    tape
    0.47
    双
    0.45
     دوب
    0.45
    雙
    0.44
     tapes
    0.44
    POSITIVE LOGITS
     NIN
    0.66
    Lloyd
    0.55
     Lloyd
    0.55
     Nin
    0.54
     nin
    0.52
     ninja
    0.47
     Ninja
    0.43
    нин
    0.43
    忍
    0.41
     элемента
    0.41
    Activations Density 0.001%

    No Known Activations