© 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. 110996
    Prev
    Next
    INDEX
    Explanations

    field office

    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
     sayuran
    -0.84
     burbu
    -0.78
     поддержки
    -0.78
     Voyage
    -0.78
    ยนต์
    -0.76
    methane
    -0.75
    atist
    -0.75
    νω
    -0.74
    itais
    -0.73
     otot
    -0.73
    POSITIVE LOGITS
     persistence
    1.09
    Lateral
    1.04
    Persistence
    1.02
     Lateral
    1.00
     lateral
    0.98
    beacon
    0.95
     piv
    0.93
    Beacon
    0.91
    persistence
    0.90
     beacon
    0.89
    Activations Density 0.032%

    No Known Activations