© 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. 75451
    Prev
    Next
    INDEX
    Explanations

    print contexts

    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
    borderSide
    -1.73
    ⢅
    -1.60
    sid
    -1.55
     технологии
    -1.52
     beiden
    -1.52
    actéristi
    -1.49
     \
    -1.47
    ᠂
    -1.45
     $
    -1.45
     других
    -1.45
    POSITIVE LOGITS
    '
    1.56
     theres
    1.55
     or
    1.52
    していると
    1.45
    rů
    1.45
     slecht
    1.45
     gối
    1.39
     geloof
    1.38
    脸上
    1.37
     民宿
    1.35
    Activations Density 0.006%

    No Known Activations