© 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. 9-GEMMASCOPE-2-RES-16K
    7. 2831
    Prev
    Next
    INDEX
    Explanations

    names and technical terms

    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_9_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ,
    0.99
     JV
    0.90
     trance
    0.87
    ၊
    0.84
     BMS
    0.84
     gentleman
    0.82
     manuscript
    0.79
    Se
    0.78
     przypadku
    0.77
    .
    0.77
    POSITIVE LOGITS
    is
    1.30
    ির
    1.30
    tion
    1.18
    ك
    1.17
    tions
    1.17
    ى
    1.11
    م
    1.08
    ture
    1.07
    اد
    1.07
    erà
    1.07
    Activations Density 0.024%

    No Known Activations