© 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. 8414
    Prev
    Next
    INDEX
    Explanations

    NYC places and events

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     ~=
    -1.16
     Fähigkeit
    -1.10
     stärker
    -1.09
    Вариант
    -1.02
    piew
    -1.02
    ここは
    -1.02
    夕食
    -1.02
     beträ
    -1.00
    Тел
    -1.00
    becoming
    -0.99
    POSITIVE LOGITS
     NYC
    1.65
     Brooklyn
    1.37
    NYC
    1.34
     NY
    1.28
     NYPD
    1.22
    nyc
    1.20
     Manhattan
    1.18
    Brooklyn
    1.17
     Bronx
    1.12
    NY
    1.06
    Activations Density 0.427%

    No Known Activations