© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 1820
    Prev
    Next
    INDEX
    Explanations

    mathematical notation separators

    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
    }>
    
    -1.01
    Date
    -0.96
    ω
    -0.96
    𝒙
    -0.95
     resté
    -0.95
     mellom
    -0.93
     of
    -0.92
     einschließlich
    -0.88
    docx
    -0.88
     ajutor
    -0.87
    POSITIVE LOGITS
     where
    1.60
     so
    1.38
    Curios
    1.05
    Πηγή
    1.05
    いわゆる
    1.00
     Therapies
    0.99
     cairan
    0.98
    哢
    0.96
     with
    0.96
     for
    0.95
    Activations Density 0.032%

    No Known Activations