© 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. 32081
    Prev
    Next
    INDEX
    Explanations

    quoted speech followed by a determiner

    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
    ز
    0.56
    ج
    0.51
     hatte
    0.50
    ش
    0.50
    س
    0.48
     btw
    0.47
     cuz
    0.47
     siehe
    0.47
     uh
    0.46
     jestem
    0.46
    POSITIVE LOGITS
    a
    0.57
    an
    0.57
    the
    0.51
    every
    0.46
    ા
    0.44
    лом
    0.44
    それが
    0.43
    eigen
    0.43
    ಥವಾ
    0.42
    ılan
    0.42
    Activations Density 0.010%

    No Known Activations