© 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. 76110
    Prev
    Next
    INDEX
    Explanations

    courtly romantic literature

    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
     incumb
    -0.81
     anglaise
    -0.81
    nahm
    -0.74
    _))
    -0.73
    購入した
    -0.71
     priest
    -0.71
     Trapp
    -0.71
     Dermal
    -0.71
     arom
    -0.70
     priestly
    -0.70
    POSITIVE LOGITS
     songs
    1.05
     court
    1.02
     trou
    1.01
     Trou
    0.98
     Proven
    0.93
    Trou
    0.90
     Court
    0.89
     COURT
    0.88
    trou
    0.84
     Minne
    0.84
    Activations Density 0.032%

    No Known Activations