© 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. 3178
    Prev
    Next
    INDEX
    Explanations

    placeholders and variable names

    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
    {}'.
    2.63
    {}".
    2.50
    '.$
    1.91
    и
    1.84
    {{
    1.62
    {}",
    1.61
    bearers
    1.58
    {$
    1.55
     podamos
    1.54
    ление
    1.48
    POSITIVE LOGITS
    -_
    2.27
    MSFontService
    1.82
    -_-
    1.57
    |_
    1.54
    Bismillahirrah
    1.49
    ibfk
    1.46
    \{-\
    1.37
    '_
    1.32
    .__
    1.30
    ._
    1.24
    Activations Density 0.219%

    No Known Activations