© 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. 233516
    Prev
    Next
    INDEX
    Explanations

    foreign or mixed languages

    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
     prescriptive
    0.47
    y
    0.44
    matically
    0.44
    ció
    0.42
     Notifications
    0.41
    neath
    0.41
     Eld
    0.41
    却没有
    0.40
    rau
    0.40
    说明
    0.40
    POSITIVE LOGITS
     さ
    0.55
     حساس
    0.54
    ｵ
    0.54
     влас
    0.52
     buon
    0.50
     環境
    0.50
     žel
    0.49
     ген
    0.48
     майже
    0.47
    บัน
    0.47
    Activations Density 0.000%

    No Known Activations