© 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. 68132
    Prev
    Next
    INDEX
    Explanations

    beginning of specific entities

    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
     těchto
    -1.88
     gastronomía
    -1.85
    ᾠ
    -1.84
     görüntüsü
    -1.82
     kağı
    -1.77
    
    -1.74
    给他们
    -1.74
     faciliter
    -1.73
     THESE
    -1.70
     этих
    -1.69
    POSITIVE LOGITS
     with
    3.33
     his
    2.61
     at
    2.39
     M
    2.09
     E
    2.08
     R
    2.06
     P
    2.03
     T
    2.03
     H
    2.02
     in
    1.99
    Activations Density 0.027%

    No Known Activations