© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12846
    Prev
    Next
    INDEX
    Explanations

    special characters and delimiters

    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
     what
    -2.27
     часу
    -2.08
    s
    -2.06
     those
    -2.03
    ~!
    -1.93
     six
    -1.89
    ?』
    -1.89
     out
    -1.89
    ~。
    -1.85
    ・・。
    -1.85
    POSITIVE LOGITS
    為に
    2.52
    えっ
    2.11
    だけではなく
    1.97
     .........
    1.96
     boî
    1.95
     ........
    1.92
     indiquer
    1.92
     "
    1.87
     "*
    1.82
    だけでなく
    1.82
    Activations Density 0.043%

    No Known Activations