© 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. 31-GEMMASCOPE-2-RES-262K
    7. 20586
    Prev
    Next
    INDEX
    Explanations

    ordering service, cement tile, former bag, range numbers, ISBT terminal, proxy client, pride month, humidifiers

    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_31_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
     Ար
    0.38
    dauer
    0.37
    であろう
    0.37
     industrious
    0.35
     обоих
    0.35
     చ
    0.35
     обще
    0.35
    ాల్
    0.35
     지방
    0.35
     स्त्रीलिंग
    0.35
    POSITIVE LOGITS
    I
    0.39
     beyond
    0.39
    कभी
    0.38
     ,
    0.38
     nodes
    0.38
     block
    0.37
     thi
    0.37
    Particles
    0.37
    更好
    0.36
     particles
    0.36
    Activations Density 0.087%

    No Known Activations