© 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. 30263
    Prev
    Next
    INDEX
    Explanations

    hi followed by words like fi, ppo, est

    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
     powied
    1.29
    ني
    1.22
     밝혔
    1.06
    ز
    1.06
    لية
    1.03
    $),
    1.01
    ק
    1.01
     lanz
    1.00
    $"
    0.98
    }/
    0.96
    POSITIVE LOGITS
     hi
    1.23
    ıyla
    1.12
    다
    1.09
    hi
    1.08
    os
    1.02
    ang
    1.01
    ab
    1.00
    na
    0.96
     nutrients
    0.95
     यस
    0.95
    Activations Density 0.005%

    No Known Activations