© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 85578
    Prev
    Next
    INDEX
    Explanations

    re thinking or looking

    np_acts-logits-general · gemini-2.5-flash-lite

    numbers and descriptive words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ભા
    0.48
    ඵ
    0.44
    ሖ
    0.43
    Ⴖ
    0.43
     thải
    0.43
    σμ
    0.42
    }}=(
    0.42
     Tarifleri
    0.42
    ຄ
    0.42
    ស្រាយ
    0.42
    POSITIVE LOGITS
    esque
    0.52
    izing
    0.48
     around
    0.47
     during
    0.46
     accusing
    0.46
     Around
    0.45
    itarian
    0.44
     on
    0.44
     within
    0.44
    iencing
    0.43
    Activations Density 0.001%

    No Known Activations