© 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. 12049
    Prev
    Next
    INDEX
    Explanations

    biographical facts and dates

    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
    Бер
    -1.45
     monté
    -1.41
     tył
    -1.41
     essayé
    -1.40
    Бар
    -1.38
    ↀ
    -1.34
    鰓
    -1.33
     Якщо
    -1.33
     będzie
    -1.28
     stolet
    -1.27
    POSITIVE LOGITS
     it
    1.84
     here
    1.82
     and
    1.68
    ありますが
    1.65
     why
    1.65
     though
    1.59
     realizando
    1.58
     you
    1.54
     Other
    1.45
     vielen
    1.45
    Activations Density 0.077%

    No Known Activations