© 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. 247843
    Prev
    Next
    INDEX
    Explanations

    foreign or specific nouns

    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
     갖
    0.46
    টেও
    0.45
     degener
    0.44
     스트
    0.42
    Ale
    0.42
     추진
    0.42
    ävä
    0.41
     경험
    0.41
    레
    0.41
     trek
    0.41
    POSITIVE LOGITS
    нять
    0.46
    씁
    0.46
     سپورټ
    0.46
     Oficial
    0.44
     ಪುಸ್ತಕ
    0.44
     apresentar
    0.44
     oficial
    0.43
     affixed
    0.43
    شارة
    0.42
     đươ
    0.42
    Activations Density 0.001%

    No Known Activations