© 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-16K
    7. 13070
    Prev
    Next
    INDEX
    Explanations

    options for calling or browsing

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

    Guanciale, linked lists, encomienda, Chili Dog

    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_16k_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
    ந்திர
    0.56
    جميع
    0.52
     Lann
    0.50
     korišten
    0.48
    뗑
    0.47
     tantas
    0.47
    خور
    0.47
    Parrocchia
    0.47
    緘
    0.46
     ერთ
    0.46
    POSITIVE LOGITS
    т
    0.57
     т
    0.45
     शुक्ल
    0.45
     воду
    0.45
     Т
    0.43
     ట
    0.42
     त्रिपाठी
    0.42
     डीएनए
    0.41
     recapture
    0.41
     scan
    0.41
    Activations Density 0.002%

    No Known Activations