© 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. 10-GEMMASCOPE-RES-131K
    7. 1467
    Prev
    Next
    INDEX
    Explanations

    operatorname, anxiety, Production, Many, Q

    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_10/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
     it
    -2.39
     there
    -2.20
     this
    -1.84
     increase
    -1.80
    ,
    -1.77
     here
    -1.73
     harten
    -1.72
    这篇
    -1.70
    indest
    -1.64
     only
    -1.63
    POSITIVE LOGITS
     Þ
    1.82
    декват
    1.78
    tées
    1.77
    𐬹
    1.73
     kWh
    1.73
    quarter
    1.66
     Testo
    1.66
    urants
    1.66
    σης
    1.66
    跸
    1.65
    Activations Density 0.000%

    No Known Activations