© 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. 63705
    Prev
    Next
    INDEX
    Explanations

    Northwest, NW, and Northwestern

    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
    mparas
    -0.79
     $($
    -0.76
     speculations
    -0.74
    aneamente
    -0.73
    āci
    -0.72
     menikmati
    -0.72
    Interesting
    -0.71
     jednot
    -0.70
    鰻
    -0.68
     Ausstattung
    -0.67
    POSITIVE LOGITS
     NW
    1.25
    NW
    1.05
     Northwest
    0.91
     Nw
    0.84
    Northwest
    0.83
     nw
    0.83
    西北
    0.83
     northwest
    0.78
    Nw
    0.76
     paired
    0.76
    Activations Density 0.027%

    No Known Activations