© 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. 32144
    Prev
    Next
    INDEX
    Explanations

    cyclic group generators

    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
    ن
    1.00
    as
    0.94
    ン
    0.91
    ad
    0.89
    in
    0.88
    an
    0.85
    ir
    0.82
    د
    0.82
    i
    0.79
    ي
    0.79
    POSITIVE LOGITS
     כש
    0.76
    もら
    0.75
    К
    0.74
     ამ
    0.69
     threaded
    0.68
     põ
    0.68
     thats
    0.66
    mst
    0.66
    簱
    0.66
     आर
    0.66
    Activations Density 0.002%

    No Known Activations