© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 34194
    Prev
    Next
    INDEX
    Explanations

    variety

    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
     многие
    0.88
    ק
    0.83
    ai
    0.82
    ルの
    0.81
    ुक
    0.75
    ف
    0.73
     отлича
    0.71
    на
    0.71
    ري
    0.70
    á
    0.70
    POSITIVE LOGITS
    し
    1.00
    ل
    0.88
    ψ
    0.76
    주고
    0.75
    i
    0.74
    l
    0.74
    必要な
    0.72
    дцать
    0.71
    ಕ್ರಮ
    0.71
    間で
    0.71
    Activations Density 0.003%

    No Known Activations