© 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. 158383
    Prev
    Next
    INDEX
    Explanations

    input, tasks, or operations

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

    comparing fees, removing features, crime scenes, plots

    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
     ці
    0.56
    AVY
    0.54
     願い
    0.52
     Цуки
    0.49
     Волго
    0.48
     имущества
    0.46
    𝗜
    0.46
    IENCE
    0.46
     Украине
    0.46
     impartiality
    0.46
    POSITIVE LOGITS
    内
    0.51
    下载
    0.50
    運営
    0.48
    菜单
    0.47
    任务
    0.46
    供应商
    0.46
    더
    0.45
    结算
    0.45
    输入
    0.45
    场
    0.45
    Activations Density 0.001%

    No Known Activations