© 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. 28494
    Prev
    Next
    INDEX
    Explanations

    《 followed by titles, < followed by code

    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
     for
    1.26
    ار
    1.11
    8
    1.09
    ad
    1.05
    7
    1.05
     at
    1.03
    9
    1.03
    ay
    1.02
    ۸
    0.98
    ۷
    0.96
    POSITIVE LOGITS
    ي
    1.57
    י
    1.45
    i
    1.31
    d
    1.09
    '
    1.04
    もら
    1.02
    ה
    0.98
    יות
    0.94
    و
    0.94
    k
    0.93
    Activations Density 0.001%

    No Known Activations