© 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. 10-GEMMASCOPE-RES-131K
    7. 119870
    Prev
    Next
    INDEX
    Explanations

    history and origins

    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
    Pokud
    -1.50
     сьогодні
    -1.46
    atized
    -1.44
    Kelebihan
    -1.41
    ícias
    -1.34
    Kesimpulan
    -1.32
    没有
    -1.30
    踯
    -1.28
    越來
    -1.28
    ("/{
    -1.27
    POSITIVE LOGITS
     of
    1.45
     türk
    1.25
     politika
    1.23
    頃の
    1.15
     deliverance
    1.15
     kult
    1.13
     was
    1.06
    ("")
    1.05
     in
    1.04
     it
    1.04
    Activations Density 0.211%

    No Known Activations