© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 220512
    Prev
    Next
    INDEX
    Explanations

    place names and their suffixes

    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
    Not in Any Lists

    No Comments

    Negative Logits
     روستا
    0.58
     villages
    0.51
    乡村
    0.47
     miejscowości
    0.47
    村
    0.47
     സ്ഥല
    0.45
     wsi
    0.45
     countryside
    0.44
     Villages
    0.43
     villagers
    0.43
    POSITIVE LOGITS
    continuous
    0.47
     continuous
    0.46
     Continuous
    0.45
    Continuous
    0.43
    連續
    0.40
    連続
    0.39
     ]]
    0.39
     연속
    0.38
    Tul
    0.38
     Miami
    0.38
    Activations Density 0.003%

    No Known Activations