© 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. 76396
    Prev
    Next
    INDEX
    Explanations

    police and federal officials

    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
     geothermal
    -0.76
    硕士
    -0.75
    simulate
    -0.75
    mordial
    -0.74
    Desen
    -0.70
     meetings
    -0.69
     paiement
    -0.68
     娜
    -0.68
    steroid
    -0.68
     torpedo
    -0.67
    POSITIVE LOGITS
     Portland
    0.99
    Portland
    0.93
     protesters
    0.92
     portland
    0.92
     plywood
    0.90
     curfew
    0.89
     voren
    0.86
     protester
    0.81
     Louisville
    0.81
     شام
    0.79
    Activations Density 0.005%

    No Known Activations