© 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. 22-GEMMASCOPE-RES-131K
    7. 34263
    Prev
    Next
    INDEX
    Explanations

    zoning and land use plans

    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_22/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
    initialise
    -1.46
    whence
    -1.43
    是怎么回事
    -1.36
    possibly
    -1.35
    どうやって
    -1.34
     קצ
    -1.34
    ěji
    -1.33
    えっ
    -1.31
    truly
    -1.31
     وليس
    -1.30
    POSITIVE LOGITS
     on
    1.56
     zoning
    1.34
     without
    1.31
     it
    1.30
     for
    1.30
     if
    1.30
     groundwater
    1.30
     city
    1.29
     residents
    1.29
     municipal
    1.28
    Activations Density 0.013%

    No Known Activations