© 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. 137156
    Prev
    Next
    INDEX
    Explanations

    huge investment in exports

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

    list items

    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
     T
    0.51
     D
    0.49
     averaging
    0.45
     Mayan
    0.44
     Gracie
    0.44
    yt
    0.44
     Citrus
    0.43
    $
    0.42
     Shelby
    0.42
     Mont
    0.42
    POSITIVE LOGITS
     deixando
    0.57
     tłumac
    0.57
     insieme
    0.54
    ANGMAR
    0.54
     deixe
    0.54
     peł
    0.52
     کنیم
    0.52
     públicas
    0.51
     sottop
    0.51
     препят
    0.51
    Activations Density 0.000%

    No Known Activations