© 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. 10-GEMMASCOPE-RES-131K
    4. 21798
    Prev
    Next
    INDEX
    Explanations

    operators and special characters

    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_10/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
     does
    -2.23
     may
    -2.19
     offers
    -2.14
     might
    -2.13
     cannot
    -2.11
    </h4>
    -2.09
     could
    -2.08
     was
    -2.06
     provides
    -2.06
     (
    -2.05
    POSITIVE LOGITS
     türkiye
    2.08
    📨
    1.90
    nements
    1.84
     utiliser
    1.84
     acheter
    1.84
    klart
    1.81
    螃
    1.79
     gezel
    1.77
     consulter
    1.73
     anadolu
    1.71
    Activations Density 0.043%

    No Known Activations