© 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. 65900
    Prev
    Next
    INDEX
    Explanations

    I followed by verb

    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
     THANKS
    -1.73
     Departement
    -1.72
     WHILE
    -1.70
     WHEN
    -1.70
     construire
    -1.63
     ´
    -1.60
    pointments
    -1.53
    pearance
    -1.50
     عندما
    -1.48
    
    -1.48
    POSITIVE LOGITS
     they
    2.11
     it
    2.09
     about
    1.92
     that
    1.88
     another
    1.77
    鍇
    1.75
    Kedua
    1.75
     孩子
    1.73
     this
    1.66
    rophes
    1.65
    Activations Density 0.108%

    No Known Activations