© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 92390
    Prev
    Next
    INDEX
    Explanations

    Championship standings

    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
     Sediment
    -0.78
    Sediment
    -0.72
    naf
    -0.66
    quirrels
    -0.66
    燼
    -0.66
    Lipid
    -0.65
     Contribution
    -0.64
     Resorts
    -0.63
     Remover
    -0.63
     currency
    -0.61
    POSITIVE LOGITS
    CAI
    0.76
     Sarawak
    0.71
    urope
    0.71
    setPos
    0.67
    一听
    0.65
    blessed
    0.64
     arrayList
    0.64
    writeTo
    0.64
    leaving
    0.63
    breadcrumb
    0.63
    Activations Density 0.060%

    No Known Activations