© 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. 97942
    Prev
    Next
    INDEX
    Explanations

    Multiculturalism

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

    English varieties

    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
    อาจ
    0.50
    और
    0.50
    类似
    0.45
    Admiral
    0.44
    ວຍ
    0.43
    յ
    0.43
    我
    0.43
    㑹
    0.43
    していた
    0.42
    훙
    0.42
    POSITIVE LOGITS
     compradores
    0.50
     búsqueda
    0.46
     vertrou
    0.46
     לח
    0.46
     sadd
    0.45
     niets
    0.45
     সবকিছু
    0.44
     뭘
    0.44
     samym
    0.43
     cabeza
    0.43
    Activations Density 0.001%

    No Known Activations