© 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. 40-GEMMASCOPE-2-RES-262K
    7. 199
    Prev
    Next
    INDEX
    Explanations

    place names and geographical features

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Warszawie
    0.56
    ogyakarta
    0.55
     Eesti
    0.53
     Städte
    0.53
    နိုင်ငံ
    0.52
     Prêmio
    0.52
     Hauptstadt
    0.52
     शहरों
    0.52
    劻
    0.52
     Azərbaycan
    0.51
    POSITIVE LOGITS
    be
    0.56
     B
    0.55
    B
    0.55
     forest
    0.54
     ponds
    0.53
     hill
    0.52
     I
    0.49
    P
    0.49
     P
    0.49
     lake
    0.49
    Activations Density 0.006%

    No Known Activations