© 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. 7171
    Prev
    Next
    INDEX
    Explanations

    recall and service bulletins

    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
    jiang
    -0.79
    ická
    -0.77
     lẫn
    -0.77
     zdravot
    -0.77
    <0xBA>
    -0.77
    trze
    -0.73
    də
    -0.73
     Veer
    -0.72
     License
    -0.71
     évalu
    -0.70
    POSITIVE LOGITS
     bulletin
    1.55
     recall
    1.55
     bulletins
    1.26
     recalls
    1.16
     updated
    1.16
    bulletin
    1.13
    recall
    1.13
     modification
    1.11
     Recall
    1.10
    Recall
    1.09
    Activations Density 0.012%

    No Known Activations