© 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. 10-GEMMASCOPE-RES-131K
    7. 101065
    Prev
    Next
    INDEX
    Explanations

    little or big

    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
    锨
    -2.11
     }}$}
    -1.91
    tache
    -1.90
     Their
    -1.88
    蜮
    -1.78
    
    -1.78
    ꦁ
    -1.78
    逦
    -1.78
     afrontar
    -1.77
     lavoratori
    -1.77
    POSITIVE LOGITS
    "
    2.17
    -
    2.11
    หรือ
    1.94
     רוצה
    1.81
    tserrat
    1.80
     ―
    1.77
     ‚
    1.75
    ‟
    1.73
     tremend
    1.73
     siendo
    1.72
    Activations Density 0.002%

    No Known Activations