© 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. 2350
    Prev
    Next
    INDEX
    Explanations

    setting a record

    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
    あが
    -0.76
     bilhões
    -0.73
     chanted
    -0.71
    cessions
    -0.71
     darted
    -0.70
    yne
    -0.68
    olt
    -0.68
    only
    -0.68
    eme
    -0.67
    MATCH
    -0.67
    POSITIVE LOGITS
     record
    3.81
     records
    3.55
    record
    2.92
    records
    2.80
    Records
    2.48
     Records
    2.47
    RECORD
    2.45
    Record
    2.42
     Record
    2.38
     RECORDS
    2.38
    Activations Density 0.028%

    No Known Activations