© 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. 11743
    Prev
    Next
    INDEX
    Explanations

    Arthur

    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
    I
    1.30
    1
    1.20
    tól
    1.18
    6
    1.17
    ش
    1.13
    uia
    1.06
    0
    1.05
    it
    1.02
    4
    1.02
    Y
    1.00
    POSITIVE LOGITS
    ר
    1.17
     Меня
    1.14
     isomorphism
    1.02
     Arthur
    1.00
    ע
    0.98
    ления
    0.98
     Еще
    0.96
     Интере
    0.94
    你
    0.93
    ۔
    0.92
    Activations Density 0.002%

    No Known Activations