© 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. 65461
    Prev
    Next
    INDEX
    Explanations

    vendor contracts and services

    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
    .~
    -0.92
    ruma
    -0.91
    ٰ
    -0.82
    +:+
    -0.81
     schemes
    -0.80
     fwd
    -0.80
     nominees
    -0.79
    Рекомен
    -0.79
    ();?>
    -0.78
     {?}
    -0.77
    POSITIVE LOGITS
     contract
    1.41
     vendor
    1.25
     Contract
    1.06
     contractor
    1.04
    Contract
    1.03
     vendors
    1.01
    Vendor
    0.98
    CONTRACT
    0.97
     Contractor
    0.97
     VEND
    0.94
    Activations Density 0.008%

    No Known Activations