© 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. 3370
    Prev
    Next
    INDEX
    Explanations

    poem about or on subjects

    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
    字符串
    0.91
    acchati
    0.85
    Denote
    0.81
     другой
    0.80
     theorem
    0.80
    ()
    0.80
    ()}
    0.80
    ();
    0.79
    altra
    0.79
     altra
    0.79
    POSITIVE LOGITS
     the
    1.27
     Death
    1.18
     Australia
    1.17
     California
    1.06
     five
    1.06
     Japan
    1.06
     three
    1.04
     Israel
    1.04
     Virgin
    1.03
     Venezuela
    1.03
    Activations Density 0.255%

    No Known Activations