© 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. 51690
    Prev
    Next
    INDEX
    Explanations

    Spanish and Italian verb endings

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

    divided by category

    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
     оці
    0.60
     від
    0.59
     ці
    0.57
     enkel
    0.56
     під
    0.54
     ізо
    0.53
     resulted
    0.52
    적
    0.52
     кі
    0.52
     відбувається
    0.52
    POSITIVE LOGITS
    ísima
    0.61
    ísim
    0.60
    ímos
    0.60
    Nombre
    0.59
    Cliente
    0.58
    objeto
    0.56
    bí
    0.56
     mediante
    0.55
     maravill
    0.55
     legít
    0.54
    Activations Density 0.010%

    No Known Activations