© 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. 28421
    Prev
    Next
    INDEX
    Explanations

    Chinese, schools, foreign words

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

    ancient philosophies and traditions

    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
    หมาย
    0.42
     earthenware
    0.41
     anthropological
    0.40
    鉾
    0.40
    माने
    0.38
    oxides
    0.38
    埕
    0.38
     typhoid
    0.37
    olicy
    0.37
     carbonate
    0.36
    POSITIVE LOGITS
     notor
    0.46
     revise
    0.44
     الدوري
    0.43
     uczni
    0.43
    Teach
    0.43
    パス
    0.42
     تلاميذ
    0.42
    邈
    0.42
    圯
    0.41
    Schools
    0.40
    Activations Density 0.021%

    No Known Activations