© 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. 60700
    Prev
    Next
    INDEX
    Explanations

    Salisbury, Wiltshire, Rowan University

    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
     ballad
    -0.98
     ballads
    -0.73
    xygen
    -0.71
     equ
    -0.70
     Taur
    -0.69
     antioxidant
    -0.69
     Ballad
    -0.69
    perasi
    -0.68
     Ferr
    -0.68
    Threading
    -0.68
    POSITIVE LOGITS
     Salisbury
    1.95
     Wiltshire
    1.32
    isbury
    1.20
    Rowan
    0.94
     Rowan
    0.94
     Ames
    0.90
     Amiens
    0.85
    cheidet
    0.81
     Rhodesia
    0.81
    kız
    0.79
    Activations Density 0.028%

    No Known Activations