© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84370
    Prev
    Next
    INDEX
    Explanations

    dragon or dragonflies

    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
    (!)
    -1.88
     yako
    -1.80
    (“
    -1.73
    茈
    -1.68
     ¡¡
    -1.68
    â
    -1.68
    ''.
    -1.66
    when
    -1.66
     ſub
    -1.65
     sandero
    -1.65
    POSITIVE LOGITS
     pomocou
    1.72
     avid
    1.70
    硖
    1.67
    璈
    1.53
    ிக்க
    1.52
     use
    1.52
    "> 
    1.50
    alitions
    1.49
     stout
    1.47
     ponen
    1.47
    Activations Density 0.015%

    No Known Activations