© 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. 5785
    Prev
    Next
    INDEX
    Explanations

    start, beginning, initial

    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
    cbind
    0.63
    colorbar
    0.62
    ંદ
    0.61
    setVerticalGroup
    0.59
    urably
    0.59
    その他の
    0.59
     дописа
    0.59
     fclose
    0.59
    とっても
    0.59
    ̻
    0.59
    POSITIVE LOGITS
     initial
    3.85
     initially
    3.77
     starting
    3.72
     start
    3.62
     first
    3.51
    Initial
    3.48
     beginning
    3.46
    เริ่มต้น
    3.44
     starts
    3.43
     시작
    3.41
    Activations Density 2.259%

    No Known Activations