© 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. 160970
    Prev
    Next
    INDEX
    Explanations

    new laws, largest entertainment, maximum performance

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

    enough capacity

    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
     Selenium
    0.50
    )=
    0.49
    mango
    0.49
     scall
    0.48
     কালো
    0.47
     एपल
    0.47
     सुगंध
    0.46
    RESET
    0.46
    aden
    0.45
     ส่ง
    0.45
    POSITIVE LOGITS
     takePhotoButton
    0.42
    烪
    0.42
    ا
    0.42
    उन्
    0.41
     atteggi
    0.41
    igment
    0.40
     crosses
    0.40
    𝗋
    0.39
     ales
    0.39
     motorcycl
    0.39
    Activations Density 0.001%

    No Known Activations