© 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. 120852
    Prev
    Next
    INDEX
    Explanations

    foreign language words

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

    even in challenging circumstances

    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
     ара
    0.44
    //$
    0.43
     shrines
    0.41
    ете
    0.41
    뜸
    0.41
    Спасибо
    0.40
     लेणी
    0.39
     Кам
    0.38
    ັ
    0.38
     हिम
    0.38
    POSITIVE LOGITS
     proie
    0.50
     clasific
    0.47
     zegt
    0.47
    sproz
    0.46
     betrieb
    0.46
     poziom
    0.46
     spricht
    0.46
     repres
    0.46
     poważ
    0.46
     widers
    0.46
    Activations Density 0.000%

    No Known Activations