© 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. 16-GEMMASCOPE-2-RES-262K
    7. 29466
    Prev
    Next
    INDEX
    Explanations

    source file paths

    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
    ס
    1.02
    מ
    1.01
    ص
    0.88
    ש
    0.88
    та
    0.85
    א
    0.82
    もら
    0.80
    י
    0.75
    ח
    0.75
    وست
    0.73
    POSITIVE LOGITS
    ᇁ
    0.88
    ă
    0.78
     Therapeutics
    0.75
     have
    0.73
     you
    0.71
     are
    0.71
    ණු
    0.71
    {
    0.70
    _
    0.69
     OMC
    0.68
    Activations Density 0.009%

    No Known Activations