© 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. 53712
    Prev
    Next
    INDEX
    Explanations

    Microwave Oven

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

    CPE devices recording

    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
    晧
    0.55
    旄
    0.48
     طريقة
    0.46
    短信
    0.46
    ন্থা
    0.45
    这不是
    0.45
    嘉宾
    0.45
    ጴ
    0.44
    烜
    0.44
    糗
    0.44
    POSITIVE LOGITS
     differentiated
    0.47
     redistribution
    0.47
     içerisinde
    0.46
     oto
    0.45
     ven
    0.45
    じる
    0.45
     severity
    0.44
     DBE
    0.44
     b
    0.44
     staged
    0.44
    Activations Density 0.000%

    No Known Activations