© 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. 12005
    Prev
    Next
    INDEX
    Explanations

    words in other languages

    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
     prodot
    -1.38
    美味しく
    -1.34
     but
    -1.32
    __':
    -1.32
     months
    -1.30
     also
    -1.27
    ↵↵
    -1.27
     risult
    -1.27
    יך
    -1.27
     inclui
    -1.26
    POSITIVE LOGITS
     extranjeros
    1.46
    hauled
    1.27
     другие
    1.26
     другим
    1.22
     their
    1.21
     cristianos
    1.20
     swoje
    1.20
     остальные
    1.20
    其他
    1.18
    arranging
    1.16
    Activations Density 0.003%

    No Known Activations