© 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. 26914
    Prev
    Next
    INDEX
    Explanations

    foreign language words, code snippets

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

    typescript imports

    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
     or
    0.56
    ↵↵
    0.55
     nhưng
    0.53
     but
    0.53
     hoặc
    0.52
    |
    0.52
     atau
    0.50
    或
    0.50
     maar
    0.50
    га
    0.48
    POSITIVE LOGITS
    Ფ
    0.52
     भगवान
    0.48
     चाँ
    0.48
     Църква
    0.46
    भगवान
    0.46
     डिप्टी
    0.46
     সেনাবাহিনীকে
    0.46
    மார
    0.44
    MsgCallBack
    0.44
     정의역
    0.44
    Activations Density 0.000%

    No Known Activations