© 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. 115381
    Prev
    Next
    INDEX
    Explanations

    convinced that, crazy adventure

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

    inspire and encourage development

    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
    града
    0.44
    人民政府
    0.44
    质量
    0.43
    礽
    0.43
    此时
    0.42
    创立
    0.42
    虢
    0.41
    рованная
    0.41
    ance
    0.40
    转移
    0.40
    POSITIVE LOGITS
     aerob
    0.47
     chemically
    0.43
     পোকামাকড়
    0.43
     GEAR
    0.43
     CHANGE
    0.42
     Pearls
    0.42
    掻
    0.42
     😊
    0.41
     ukl
    0.41
    لي
    0.41
    Activations Density 0.001%

    No Known Activations