© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 15458
    Prev
    Next
    INDEX
    Explanations

    punctuation and non-latin scripts

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

    punctuation and special characters

    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
    Not in Any Lists

    No Comments

    Negative Logits
     to
    0.69
     of
    0.59
    0
    0.57
    '
    0.57
    ’
    0.54
    (
    0.52
    \
    0.51
    ਾਰ
    0.48
    IN
    0.47
    &
    0.44
    POSITIVE LOGITS
    ↵
    0.62
     বেশিরভাগ
    0.52
     Mỗi
    0.49
    ת
    0.44
     사람들이
    0.43
     ប៉ុ
    0.42
    телите
    0.42
    🎏
    0.41
    ⛵
    0.40
    Ὑ
    0.40
    Activations Density 0.002%

    No Known Activations