© 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
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9056
    Prev
    Next
    INDEX
    Explanations

    Montreal and Quebec city and province

    np_acts-logits-general · gemini-2.5-flash-lite

    Montreal, Quebec, Lausanne

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_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
    }:=
    0.43
    никова
    0.42
    делать
    0.42
    ровку
    0.40
    ?}",
    0.40
     Indones
    0.40
    тол
    0.39
    дени
    0.39
     Indonesian
    0.39
    nyt
    0.38
    POSITIVE LOGITS
     Quebec
    1.48
     Québec
    1.48
     Montreal
    1.47
     Montréal
    1.38
    Montreal
    1.34
     Qué
    1.08
     Canadiens
    1.04
    Qué
    1.02
     McGill
    0.90
    魁
    0.84
    Activations Density 0.175%

    No Known Activations