© 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. 69599
    Prev
    Next
    INDEX
    Explanations

    experience of fun

    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
     famous
    -1.92
     preghiera
    -1.59
     acoged
    -1.59
     unhappy
    -1.58
     biggest
    -1.48
     connessione
    -1.48
     many
    -1.48
     improved
    -1.46
     ultimately
    -1.46
     poate
    -1.45
    POSITIVE LOGITS
    ทั้ง
    1.63
    }\
    1.63
    AutoresizingMask
    1.52
    觧
    1.48
     of
    1.46
    읗
    1.42
     både
    1.42
    
    1.38
     חיצוניים
    1.38
    кость
    1.37
    Activations Density 0.008%

    No Known Activations