© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 98579
    Prev
    Next
    INDEX
    Explanations

    “ collaborative Unicode

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    $
    -2.88
    "
    -2.75
    le
    -2.73
    櫚
    -2.64
    ers
    -2.53
    嗵
    -2.53
    *
    -2.50
    ين
    -2.39
    '
    -2.39
     programmet
    -2.38
    POSITIVE LOGITS
     “
    2.63
     aisladas
    2.48
     “…
    2.36
    鉝
    2.27
     nincs
    2.19
     It
    2.19
    ’
    2.19
      
    2.17
    哙
    2.16
     see
    2.13
    Activations Density 0.610%

    No Known Activations