© 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. 98729
    Prev
    Next
    INDEX
    Explanations

    where Detroit

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

    Statue of Liberty and Ellis Island

    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
    柅
    0.51
     इतर
    0.48
    のかな
    0.48
     bilgiler
    0.47
     결국
    0.47
    ravés
    0.47
    冫
    0.47
     информации
    0.46
     있었다
    0.46
     Produtos
    0.45
    POSITIVE LOGITS
    at
    0.50
     anesthet
    0.48
     coastal
    0.46
    tag
    0.45
     .
    0.45
     aesthetic
    0.44
    astes
    0.43
     typedef
    0.43
    ail
    0.43
     labor
    0.42
    Activations Density 0.000%

    No Known Activations