© 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. 123990
    Prev
    Next
    INDEX
    Explanations

    error termination or exit conditions

    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
     you
    -1.78
     and
    -1.56
     \
    -1.48
     estrecha
    -1.29
     vacía
    -1.26
    bahar
    -1.23
     Resultat
    -1.23
     tény
    -1.23
     ‘‘
    -1.20
    livé
    -1.20
    POSITIVE LOGITS
     gewünschten
    1.40
    utilité
    1.34
     sienten
    1.34
     häls
    1.33
    здрав
    1.30
    Это
    1.27
    也许
    1.26
     if
    1.25
     notwendigen
    1.23
    setzer
    1.22
    Activations Density 0.007%

    No Known Activations