© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112543
    Prev
    Next
    INDEX
    Explanations

    new york city

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

    the mention of “New York” (including variations like the Polish “Nowy Jork”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    {
    -2.70
    2
    -2.28
    I
    -2.25
    8
    -2.22
    ).
    -2.06
    ’
    -2.06
    4
    -2.00
    3
    -1.96
     erhi
    -1.83
    \
    -1.82
    POSITIVE LOGITS
     expérience
    2.00
     Decreto
    1.95
     Garantie
    1.90
    🦈
    1.89
    鸶
    1.88
    鳚
    1.88
     junio
    1.86
     monstre
    1.85
     taxe
    1.83
    洗面
    1.81
    Activations Density 0.031%

    No Known Activations