© 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. 81513
    Prev
    Next
    INDEX
    Explanations

    bonds called or redeemed

    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
     underwriting
    -0.90
    ufort
    -0.84
     steer
    -0.83
     tomate
    -0.83
    ző
    -0.82
     kidney
    -0.82
     rookie
    -0.81
    cedor
    -0.80
    GridLayout
    -0.80
    steria
    -0.79
    POSITIVE LOGITS
     redemption
    1.34
     callable
    1.24
     call
    1.23
    call
    1.16
    调用
    1.07
     Redemption
    1.05
     called
    1.05
     Call
    1.04
     calling
    1.02
     callers
    1.00
    Activations Density 0.004%

    No Known Activations