© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39869
    Prev
    Next
    INDEX
    Explanations

    eyes open or closed

    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
     dépens
    -1.59
    >
    -1.58
     Seleccione
    -1.55
     réun
    -1.51
     itulah
    -1.50
     Coloque
    -1.48
     Obtén
    -1.47
     dizendo
    -1.45
     accompagner
    -1.43
     gekenn
    -1.41
    POSITIVE LOGITS
    
    1.42
     महत्वपूर्ण
    1.39
    きっかけ
    1.38
    ῎
    1.38
     tráiler
    1.34
     katkı
    1.33
     çeşitli
    1.31
     впервые
    1.31
    ޏ
    1.30
     což
    1.30
    Activations Density 0.004%

    No Known Activations