© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65528
    Prev
    Next
    INDEX
    Explanations

    sock

    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
    alpin
    -0.89
    verde
    -0.87
    ὐ
    -0.81
     linux
    -0.78
    libur
    -0.78
     gelijk
    -0.77
    小区
    -0.77
    マンド
    -0.75
    ήσει
    -0.75
    MySql
    -0.73
    POSITIVE LOGITS
     Sock
    1.40
     sock
    1.35
     poodle
    1.29
     Grease
    1.20
    sock
    1.13
     Graffiti
    1.11
    Grease
    1.09
     malt
    1.07
    Sock
    0.98
     Teen
    0.97
    Activations Density 0.023%

    No Known Activations