© 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-16K
    7. 3171
    Prev
    Next
    INDEX
    Explanations

    direct descriptions

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    。
    1.67
    。《
    1.52
    。\
    1.51
    ।
    1.48
    ။
    1.47
    ®.
    1.44
    ).
    1.44
    。【
    1.38
    。「
    1.37
    !।
    1.37
    POSITIVE LOGITS
     непосредственно
    0.99
    Read
    0.79
    Leer
    0.74
    directly
    0.67
    Registers
    0.62
    直接
    0.61
    মাই
    0.61
     diretamente
    0.61
    Direct
    0.61
    Ver
    0.60
    Activations Density 0.950%

    No Known Activations