© 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. 201278
    Prev
    Next
    INDEX
    Explanations

    numbers and percentages

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

    querying databases

    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
     ہی
    0.46
    ide
    0.45
    ویل
    0.44
    盒子
    0.44
    antia
    0.44
    қты
    0.43
    배
    0.43
    deploy
    0.43
    istet
    0.43
    ễm
    0.42
    POSITIVE LOGITS
     texto
    0.57
     なさい
    0.54
     പിന്നീട്
    0.50
     Salesforce
    0.49
     позднее
    0.48
     ս
    0.48
     نشرح
    0.48
     задач
    0.46
     পরিপ্রেক্ষিতে
    0.46
    !`
    0.46
    Activations Density 0.000%

    No Known Activations