© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7404
    Prev
    Next
    INDEX
    Explanations

    function definitions and imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hasilnya
    0.39
     දෙ
    0.38
     तीन
    0.36
    三个
    0.36
    셔서
    0.35
    偣
    0.34
     เห
    0.34
    送信
    0.34
     hilang
    0.33
     তিনটি
    0.33
    POSITIVE LOGITS
     Nucleaire
    0.45
     sogenannte
    0.40
     sogenannten
    0.38
    VERSE
    0.34
     sedimentary
    0.34
     Toen
    0.31
     Detention
    0.31
    xymatrix
    0.31
     Maverick
    0.31
     கடுமையான
    0.31
    Activations Density 0.779%

    No Known Activations