© 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. 31-GEMMASCOPE-2-RES-262K
    7. 2015
    Prev
    Next
    INDEX
    Explanations

    but I

    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
    tr
    0.31
    RESSION
    0.29
    T
    0.29
    TR
    0.29
    M
    0.29
    YOUR
    0.28
    you
    0.28
    W
    0.28
    ka
    0.27
    CO
    0.27
    POSITIVE LOGITS
     cuando
    0.34
     lors
    0.32
     عند
    0.31
     when
    0.30
     στο
    0.30
     quando
    0.30
     someday
    0.30
    ในสนาม
    0.29
     beim
    0.29
     eventuali
    0.29
    Activations Density 0.000%

    No Known Activations