© 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. 41-GEMMASCOPE-2-RES-262K
    7. 9357
    Prev
    Next
    INDEX
    Explanations

    population and municipality size

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     דבר
    0.35
    ע
    0.34
    剜
    0.32
     discredit
    0.32
     יע
    0.31
     Universo
    0.30
    πλ
    0.30
    물
    0.30
    公開
    0.30
     Liga
    0.30
    POSITIVE LOGITS
     beträgt
    0.38
    面積
    0.37
    population
    0.36
     densidad
    0.36
    habitants
    0.36
     Population
    0.35
     population
    0.35
    adients
    0.34
     població
    0.34
     bucks
    0.34
    Activations Density 0.000%

    No Known Activations