© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 13799
    Prev
    Next
    INDEX
    Explanations

    java and file paths

    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_22/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
    agerie
    -1.03
    chemise
    -0.90
    ヱ
    -0.88
    changer
    -0.85
    strator
    -0.85
    对此
    -0.83
     Sloveniji
    -0.82
    iedział
    -0.82
     éves
    -0.81
     :
    
    -0.81
    POSITIVE LOGITS
     represen
    1.01
    こんに
    0.99
     FLUID
    0.95
    सर
    0.94
     besoins
    0.94
    私たちは
    0.94
    ną
    0.93
    siempre
    0.93
     simplif
    0.92
    aunque
    0.91
    Activations Density 0.029%

    No Known Activations