© 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. 14301
    Prev
    Next
    INDEX
    Explanations

    product and what follows

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

    product launch, development, and description

    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
    LE
    1.00
    0.98
     be
    0.90
    IA
    0.89
    ED
    0.89
    .
    0.82
    ண
    0.78
    AN
    0.77
    AL
    0.75
    IL
    0.75
    POSITIVE LOGITS
     products
    1.27
     продукт
    1.20
     product
    1.13
     продукта
    1.13
     продукти
    1.13
     prodotti
    1.12
     продукты
    1.12
    продук
    1.11
     المنتج
    1.11
     produk
    1.09
    Activations Density 0.069%

    No Known Activations