© 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. 399
    Prev
    Next
    INDEX
    Explanations

    required by

    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
     OE
    -0.81
     Followed
    -0.79
     russischen
    -0.78
    通貨
    -0.77
    igrafi
    -0.76
    ٹر
    -0.75
    檜
    -0.71
     Ikea
    -0.70
     Burger
    -0.70
    宜蘭
    -0.70
    POSITIVE LOGITS
     even
    1.02
     flux
    0.92
    resolved
    0.87
     Chloride
    0.84
    гән
    0.82
     bhp
    0.81
     RESOLUTION
    0.81
     焼
    0.81
    образие
    0.81
     emailAlready
    0.79
    Activations Density 0.029%

    No Known Activations