© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 190410
    Prev
    Next
    INDEX
    Explanations

    hotel, display, and format

    np_acts-logits-general · gemini-2.5-flash-lite

    data lineage and lifecycle management

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     manifestazione
    0.49
     escog
    0.48
    ':
    0.47
     automático
    0.46
     acción
    0.45
    рованная
    0.45
     soy
    0.44
     trayectoria
    0.43
    že
    0.43
     Comunic
    0.43
    POSITIVE LOGITS
     शहरों
    0.47
    dı
    0.46
    І
    0.45
    湋
    0.45
    軖
    0.44
     аў
    0.43
    НИ
    0.43
    अन
    0.43
    ürdig
    0.43
    तात
    0.42
    Activations Density 0.002%

    No Known Activations