© 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. 242605
    Prev
    Next
    INDEX
    Explanations

    years and quantities

    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
     গান্ধীর
    0.50
     গান্ধী
    0.47
     Favorites
    0.47
     ViewGroup
    0.45
     возник
    0.44
     图
    0.44
     Active
    0.44
     বাগের
    0.43
     বিশ্ববিদ্যালয়
    0.43
     Exhibition
    0.42
    POSITIVE LOGITS
    മു
    0.53
     inmediato
    0.52
    氶
    0.52
    مصادر
    0.50
    зво
    0.49
     arrêter
    0.48
    ान्स
    0.48
    оти
    0.48
     phận
    0.48
    쇠
    0.48
    Activations Density 0.000%

    No Known Activations