© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 116075
    Prev
    Next
    INDEX
    Explanations

    GNOME and desktop environments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Kentucky
    0.60
    ת
    0.60
    ്‍
    0.51
    describe
    0.51
     испыта
    0.50
     commencing
    0.49
    i
    0.49
    зре
    0.49
    findOrFail
    0.48
    Lt
    0.48
    POSITIVE LOGITS
     TO
    0.62
     articoli
    0.60
    icas
    0.57
     electrons
    0.56
    inhos
    0.56
    )
    0.56
     gtk
    0.56
    ástico
    0.55
     anos
    0.55
    igi
    0.54
    Activations Density 0.027%

    No Known Activations