© 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. 34-GEMMASCOPE-RES-131K
    7. 78776
    Prev
    Next
    INDEX
    Explanations

    Kansas and related locations

    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_34/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
    tsburgh
    -0.81
    <%=
    -0.80
    mfenced
    -0.78
     tila
    -0.73
    =#{
    -0.72
    ifornie
    -0.72
     Pud
    -0.70
    ᴀ
    -0.69
     прине
    -0.69
    に乗り
    -0.68
    POSITIVE LOGITS
     Kansas
    3.13
    Kansas
    2.84
     Wichita
    2.47
     Topeka
    2.42
     KANSAS
    2.08
     Kans
    1.92
    Wich
    1.77
     KC
    1.70
     KU
    1.70
     KS
    1.63
    Activations Density 0.099%

    No Known Activations