© 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. 75299
    Prev
    Next
    INDEX
    Explanations

    speak in a certain way

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

    simple terms

    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
    도의
    0.63
    क्की
    0.54
    ⿶
    0.51
    도를
    0.50
    下列
    0.49
     CMR
    0.49
     Raider
    0.49
    Ба
    0.49
    Би
    0.48
     chó
    0.48
    POSITIVE LOGITS
     ისინი
    0.46
    ís
    0.46
    ın
    0.46
    kos
    0.46
     sobreviv
    0.46
     impresion
    0.45
    0
    0.44
     sombre
    0.44
    viz
    0.43
     გადა
    0.43
    Activations Density 0.001%

    No Known Activations