© 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. 58763
    Prev
    Next
    INDEX
    Explanations

    approved, accredited, recognized

    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
    generated
    -0.84
     exprim
    -0.84
     Played
    -0.78
    guided
    -0.78
    検討
    -0.77
    centered
    -0.76
    ikyuu
    -0.76
    averaged
    -0.76
    performed
    -0.75
     rifer
    -0.75
    POSITIVE LOGITS
     approved
    5.16
    approved
    3.75
    Approved
    3.48
     Approved
    3.48
     accredited
    3.22
     authorized
    3.19
     certified
    2.97
     APPROVED
    2.97
     recognized
    2.94
     registered
    2.78
    Activations Density 0.121%

    No Known Activations