© 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. 5745
    Prev
    Next
    INDEX
    Explanations

    name or title

    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
    Negative Logits
     పరిస్థి
    0.65
    ervlak
    0.63
    chend
    0.62
     اقتصاد
    0.61
     расс
    0.60
    ើរ
    0.60
    dW
    0.60
    erts
    0.60
    OutputStream
    0.60
    踩
    0.60
    POSITIVE LOGITS
     name
    4.92
     names
    4.54
     Name
    4.24
    name
    4.23
    名称
    4.08
    Name
    3.98
    名字
    3.85
     Names
    3.83
    名稱
    3.83
     naming
    3.78
    Activations Density 1.727%

    No Known Activations