© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 10936
    Prev
    Next
    INDEX
    Explanations

    rain against windows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cytokine
    0.80
     মুহাম্ম
    0.75
     didReceive
    0.73
    풉
    0.72
    遺跡
    0.71
     생성
    0.71
    覃
    0.70
    痣
    0.69
     excreted
    0.69
    咲
    0.68
    POSITIVE LOGITS
     window
    2.44
     windows
    2.44
     Window
    2.32
    Window
    2.16
    window
    2.11
    窗
    2.10
     windowsill
    2.07
     jendela
    2.05
     окна
    2.02
     ventanas
    2.02
    Activations Density 0.090%

    No Known Activations