© 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. 46121
    Prev
    Next
    INDEX
    Explanations

    division, addition, comparison, customs

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

    standard multiplication algorithm

    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
     null
    0.49
     aik
    0.46
     પાડ
    0.46
    9
    0.45
     absence
    0.45
     lak
    0.45
    4
    0.44
     okt
    0.43
     gaming
    0.43
    8
    0.43
    POSITIVE LOGITS
    時代の
    0.52
    óstico
    0.50
    க்கப்பட்ட
    0.48
     случаи
    0.48
    ার্জি
    0.47
    スメ
    0.46
    époque
    0.46
    ezas
    0.46
     सीतार
    0.46
    umam
    0.46
    Activations Density 0.000%

    No Known Activations