© 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. 8626
    Prev
    Next
    INDEX
    Explanations

    cities like London

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

    cities London Paris

    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
     ايا
    0.46
    稳
    0.41
     CITY
    0.40
    lz
    0.40
     चिंत
    0.38
     NGS
    0.38
    gaia
    0.38
    棕
    0.37
    lara
    0.37
     మరో
    0.37
    POSITIVE LOGITS
    Lond
    0.50
    🗼
    0.47
     Paris
    0.46
    der
    0.45
    Paris
    0.45
    London
    0.43
     London
    0.43
     東京
    0.42
     PARIS
    0.42
    奥运
    0.41
    Activations Density 0.150%

    No Known Activations