© 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. 36703
    Prev
    Next
    INDEX
    Explanations

    foreign words and phrases

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

    disorder, surprising, accept

    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
    栞
    0.48
     Komis
    0.46
    К
    0.46
    или
    0.45
    َه
    0.44
    ጴ
    0.44
    аль
    0.44
    тная
    0.43
    స్‌
    0.43
    주고
    0.43
    POSITIVE LOGITS
     .
    0.50
     queremos
    0.48
     comerci
    0.48
     cibo
    0.48
     comida
    0.48
     denaro
    0.48
     chcia
    0.48
     teria
    0.47
     sustit
    0.47
     coś
    0.47
    Activations Density 0.000%

    No Known Activations