© 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. 133032
    Prev
    Next
    INDEX
    Explanations

    figures and vision

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

    encapsulate business logic

    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
    menuCategory
    0.48
    ):\
    0.45
    ات
    0.45
    ق
    0.44
     mangroves
    0.44
    BURG
    0.44
    籮
    0.42
    ామ
    0.42
    जब
    0.41
    ح
    0.41
    POSITIVE LOGITS
     Suu
    0.61
     Swain
    0.54
     efic
    0.51
     еще
    0.50
     všech
    0.50
     Suárez
    0.50
     Saleh
    0.49
     ещё
    0.49
     Hernández
    0.49
     Shahid
    0.49
    Activations Density 0.000%

    No Known Activations