© 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. 203923
    Prev
    Next
    INDEX
    Explanations

    list of items

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

    conditions lasting

    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
    開発
    0.49
     razvoj
    0.47
     incessantly
    0.46
    公開
    0.42
     henceforth
    0.42
    Diss
    0.41
    聞
    0.41
    靴
    0.41
    環境
    0.40
     simultaneously
    0.40
    POSITIVE LOGITS
     टीच
    0.58
     бело
    0.48
    这点
    0.48
    <unused505>
    0.47
     tyle
    0.46
    朓
    0.44
    㡱
    0.44
    oom
    0.43
    minLength
    0.43
    柔软
    0.42
    Activations Density 0.000%

    No Known Activations