© 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. 73481
    Prev
    Next
    INDEX
    Explanations

    you an example

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

    respect, lack, harm

    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
    ف
    0.52
    وینت
    0.47
     Innoc
    0.47
    غاز
    0.46
    बरा
    0.46
    فاء
    0.45
    पुट
    0.44
    لیس
    0.44
    ب
    0.44
     و
    0.43
    POSITIVE LOGITS
    充実
    0.45
     کړئ
    0.43
    ರಿ
    0.43
    ራል
    0.42
     አሉ
    0.42
     ROOM
    0.42
     dimas
    0.41
    MATIC
    0.41
    ಿಕ
    0.40
    icin
    0.40
    Activations Density 0.008%

    No Known Activations