© 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. 117090
    Prev
    Next
    INDEX
    Explanations

    Renaissance paintings

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

    Reservations, satisfaction, code examples

    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
    ديد
    0.46
     \
    0.44
     ferment
    0.44
    اعت
    0.44
    вик
    0.44
    的名字
    0.43
    عتها
    0.43
     names
    0.42
     brewed
    0.42
     interf
    0.41
    POSITIVE LOGITS
     छात्र
    0.52
     অগ্রসর
    0.51
     取っ
    0.50
    illis
    0.50
     Tahun
    0.48
     निर्देशा
    0.48
    ச
    0.48
     berusaha
    0.47
     QuantityOnHand
    0.47
    テント
    0.46
    Activations Density 0.000%

    No Known Activations