© 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. 2132
    Prev
    Next
    INDEX
    Explanations

    article under Creative Commons license

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

    journal or equivalent

    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
     quận
    0.40
    砼
    0.38
    စိတ်အပိုင်း
    0.38
    ၾ
    0.37
    ayvachi
    0.37
    ്ലാ
    0.37
    车站
    0.37
    ังสือ
    0.36
    🧅
    0.36
    اونلو
    0.36
    POSITIVE LOGITS
    article
    0.42
    }\
    0.42
     \
    0.39
     $\
    0.37
    pl
    0.36
    TM
    0.36
     pathogenesis
    0.36
     Accepted
    0.35
     ARTICLE
    0.35
    ISSN
    0.35
    Activations Density 0.005%

    No Known Activations