© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 5382
    Prev
    Next
    INDEX
    Explanations

    html code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     terj
    1.05
     çağ
    0.94
     হিন
    0.93
     ड्रीम
    0.90
    parency
    0.89
    нется
    0.87
    িলাম
    0.86
    niają
    0.85
    ুকে
    0.84
    틋
    0.84
    POSITIVE LOGITS
    Valve
    0.85
     Although
    0.83
    Fleet
    0.83
     Vortex
    0.81
     RenderTexture
    0.80
    Although
    0.80
    blues
    0.79
    </body>
    0.78
     Volleyball
    0.78
    ＆
    0.77
    Activations Density 0.088%

    No Known Activations