© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 3918
    Prev
    Next
    INDEX
    Explanations

    country and city names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    タウン
    1.18
     townships
    1.08
    larınız
    1.05
     localidades
    1.01
    anız
    0.99
    (',',$
    0.98
     municipios
    0.97
    POSTFIELDS
    0.97
     Legislature
    0.96
     ilç
    0.96
    POSITIVE LOGITS
     пор
    1.48
    η
    1.47
    мі
    1.36
    гу
    1.36
     lus
    1.35
    ace
    1.33
     Ги
    1.32
    透
    1.31
     тре
    1.30
     PSG
    1.29
    Activations Density 0.127%

    No Known Activations