© 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. 10-GEMMASCOPE-RES-131K
    4. 118815
    Prev
    Next
    INDEX
    Explanations

    scheduling appointments

    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
     Dinas
    -2.25
    躄
    -2.14
     podemos
    -2.00
     \
    -2.00
     avec
    -1.99
     με
    -1.91
    месте
    -1.91
    can
    -1.91
     puede
    -1.90
    ICOLON
    -1.90
    POSITIVE LOGITS
     romero
    2.34
     moreno
    2.22
    哢
    2.06
     marseille
    2.02
     torres
    1.98
    过后
    1.95
     salvador
    1.95
     itſelf
    1.91
     火鍋
    1.89
     infal
    1.84
    Activations Density 0.004%

    No Known Activations