© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 55984
    Prev
    Next
    INDEX
    Explanations

    Wisconsin and its entities

    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
    POLY
    -0.86
     Niedersachsen
    -0.81
     PCT
    -0.81
     sierp
    -0.79
    אתה
    -0.78
     UNT
    -0.77
     POLY
    -0.77
     可能
    -0.77
     Fiji
    -0.76
     Sjö
    -0.76
    POSITIVE LOGITS
     Wisconsin
    3.77
    Wisconsin
    3.47
     Milwaukee
    3.16
    Milwaukee
    2.98
     WISCONSIN
    2.53
     UW
    2.39
     Wau
    2.08
    UW
    1.98
    consin
    1.85
     Wis
    1.79
    Activations Density 0.137%

    No Known Activations