© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 31181
    Prev
    Next
    INDEX
    Explanations

    load(

    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_16_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
    ներ
    0.57
     ສ
    0.55
     c
    0.54
    ূল্যে
    0.52
    ла
    0.52
     fuori
    0.52
    რ
    0.50
    ੱ
    0.50
    BPACK
    0.49
    να
    0.49
    POSITIVE LOGITS
    :
    0.56
    aren
    0.55
    *
    0.51
    ang
    0.51
    (
    0.50
     billion
    0.48
    rei
    0.47
    ickeys
    0.47
    adin
    0.46
     seben
    0.46
    Activations Density 0.001%

    No Known Activations