© 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. 55580
    Prev
    Next
    INDEX
    Explanations

    android:id="@+id/

    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
    廚房
    -0.79
     RECOGN
    -0.77
     MainActivity
    -0.71
    折磨
    -0.71
    
    -0.69
     Coen
    -0.69
    Nyt
    -0.68
     mittens
    -0.68
    inien
    -0.68
    ⠘
    -0.68
    POSITIVE LOGITS
    getId
    0.99
    getResource
    0.98
     getId
    0.94
     ids
    0.87
     resource
    0.86
     res
    0.84
     IDS
    0.82
    IDs
    0.82
     IDs
    0.82
    IDS
    0.81
    Activations Density 0.020%

    No Known Activations