© 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. 177663
    Prev
    Next
    INDEX
    Explanations

    country names and locations

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

    descriptive qualities and states

    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
     Ши
    0.46
     பண்டைய
    0.46
    све
    0.46
     분류
    0.44
    డ్‌
    0.44
     만족
    0.44
    ң
    0.43
    ров
    0.43
     Для
    0.43
     удалить
    0.43
    POSITIVE LOGITS
     dane
    0.57
     linken
    0.56
     mies
    0.55
     mulher
    0.53
     gimnas
    0.53
    a
    0.52
     sienten
    0.51
    ITATE
    0.51
     matemat
    0.50
     deles
    0.50
    Activations Density 0.002%

    No Known Activations