© 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. 238961
    Prev
    Next
    INDEX
    Explanations

    Italian troops, custom embroidered

    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
     जया
    0.42
    yb
    0.42
    typen
    0.41
    loy
    0.41
    θυ
    0.40
    ysin
    0.40
    äller
    0.39
    )+
    0.39
    omer
    0.39
    пы
    0.39
    POSITIVE LOGITS
    蔼
    0.45
     ઘટા
    0.45
     acciaio
    0.45
     zarówno
    0.43
     både
    0.42
    Нор
    0.42
    Milwaukee
    0.42
    ﻫ
    0.41
    াবলী
    0.41
     aneur
    0.41
    Activations Density 0.001%

    No Known Activations