© 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. 87197
    Prev
    Next
    INDEX
    Explanations

    Presidential Medal, District Court, Missouri Court

    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
    Hugo
    -0.82
     efectivos
    -0.79
    urare
    -0.77
     TPR
    -0.75
    czek
    -0.75
     Emilio
    -0.74
     Euse
    -0.74
     frow
    -0.73
     قبول
    -0.73
     zéro
    -0.72
    POSITIVE LOGITS
    ArrayOf
    1.02
    COC
    0.96
     listOf
    0.94
    MessageOf
    0.94
     Persons
    0.93
     crimes
    0.92
     Of
    0.92
     Ao
    0.90
     arrayOf
    0.88
     method
    0.85
    Activations Density 0.209%

    No Known Activations