© 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. 104715
    Prev
    Next
    INDEX
    Explanations

    news headlines and reports

    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
    確認ください
    -1.08
    IFICATION
    -1.07
    出色
    -1.05
     departement
    -0.98
    利亚
    -0.96
     hect
    -0.94
     msk
    -0.93
    שלום
    -0.93
    illeurs
    -0.92
     felic
    -0.92
    POSITIVE LOGITS
     also
    1.57
     you
    1.38
     that
    1.37
     yeah
    1.27
     then
    1.27
    öre
    1.20
     entire
    1.17
     we
    1.13
     I
    1.13
     there
    1.08
    Activations Density 0.003%

    No Known Activations