© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91889
    Prev
    Next
    INDEX
    Explanations

    US states and Mardi Gras

    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
    readyState
    -0.84
     Taunton
    -0.82
     Bruins
    -0.82
     arraigned
    -0.79
     mandibular
    -0.78
    бие
    -0.77
    Ocean
    -0.77
     Amman
    -0.75
     BMS
    -0.75
    partum
    -0.74
    POSITIVE LOGITS
     Indiana
    0.96
     Louisiana
    0.89
     Cajun
    0.83
    Indiana
    0.83
     наши
    0.82
     Tulsa
    0.79
    Tul
    0.78
    眼底
    0.78
    Mardi
    0.77
     Mardi
    0.76
    Activations Density 0.006%

    No Known Activations