© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59495
    Prev
    Next
    INDEX
    Explanations

    in the same way

    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_34/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
     akurat
    -0.87
     Übernach
    -0.86
    logitech
    -0.85
    特に
    -0.78
    Už
    -0.77
     berken
    -0.77
    userProfile
    -0.75
    しかも
    -0.73
    款式
    -0.73
     histó
    -0.72
    POSITIVE LOGITS
     token
    2.41
     vein
    2.34
    token
    1.98
     breath
    1.85
    vein
    1.54
     Token
    1.53
    Token
    1.51
    breath
    1.49
     tokens
    1.45
     breathe
    1.41
    Activations Density 0.013%

    No Known Activations