© 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. 88751
    Prev
    Next
    INDEX
    Explanations

    Android phone

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

    non-latin script phrases

    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
     STE
    0.48
    Ko
    0.46
    աց
    0.46
    "
    0.46
    Know
    0.44
    രീക്ഷ
    0.44
    *
    0.44
    жды
    0.44
     knives
    0.44
    Olivier
    0.43
    POSITIVE LOGITS
    坝
    0.54
     झाल
    0.50
     發
    0.50
     스마트
    0.48
     库存
    0.48
    बाह
    0.48
     შეს
    0.47
     बढ़े
    0.46
     活动
    0.46
     회사
    0.46
    Activations Density 0.000%

    No Known Activations