© 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. 29-GEMMASCOPE-2-RES-262K
    7. 145478
    Prev
    Next
    INDEX
    Explanations

    why patterns

    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_29_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    τως
    0.97
     Granted
    0.88
     turun
    0.87
    Atom
    0.86
     unserem
    0.85
     naszych
    0.84
    哪個
    0.82
     ہمارے
    0.81
    晏
    0.81
    မယ်
    0.80
    POSITIVE LOGITS
     или
    1.42
     под
    1.28
     на
    1.25
     и
    1.25
     е
    1.24
     се
    1.16
     ръ
    1.12
     ду
    1.12
     х
    1.11
     дре
    1.11
    Activations Density 0.000%

    No Known Activations