© 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. 21441
    Prev
    Next
    INDEX
    Explanations

    phrases starting with must

    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
    ooooo
    -1.83
    مشخص
    -1.80
     titolata
    -1.70
     conosco
    -1.68
    
    -1.66
    oooooo
    -1.65
     pudieron
    -1.64
    7
    -1.63
     mutiara
    -1.62
     firebaseConfig
    -1.62
    POSITIVE LOGITS
     be
    2.02
     efficacité
    1.46
     протяжении
    1.46
     产
    1.39
     другие
    1.38
     办
    1.35
    时刻
    1.34
    DockStyle
    1.33
     acheteurs
    1.30
     纳
    1.30
    Activations Density 0.013%

    No Known Activations