© 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. 85674
    Prev
    Next
    INDEX
    Explanations

    Graham Harman, graham cracker, Hilary Putnam

    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
    ۵
    1.23
    した
    1.13
    ५
    1.11
    ۴
    1.11
    ся
    1.09
    dür
    1.06
    ки
    1.05
    ین
    1.04
     роста
    1.04
    توان
    1.03
    POSITIVE LOGITS
     be
    1.55
     have
    1.23
    (
    1.22
    िंग
    1.19
     it
    1.16
    ना
    1.16
     bevel
    1.13
    ంగా
    1.12
    have
    1.12
    0
    1.09
    Activations Density 0.018%

    No Known Activations