© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 7879
    Prev
    Next
    INDEX
    Explanations

    version numbers 1.0 and 2.0

    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_65k_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
    不幸
    0.81
    መረ
    0.79
    睉
    0.79
    大多数
    0.78
    ောင့်
    0.74
    कश
    0.73
     acompaña
    0.72
     olha
    0.72
     일반적으로
    0.71
    ጠ
    0.71
    POSITIVE LOGITS
    2
    1.17
     v
    1.00
     ٢
    0.95
    ２
    0.93
     Version
    0.93
    Version
    0.93
    version
    0.92
    ٢
    0.90
     версии
    0.90
     version
    0.89
    Activations Density 0.065%

    No Known Activations