© 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. 90947
    Prev
    Next
    INDEX
    Explanations

    ranking, awards, numbers

    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
    servicios
    -0.80
    kkende
    -0.77
    defs
    -0.76
    uploader
    -0.75
     Services
    -0.73
     services
    -0.72
    XV
    -0.72
    conjugated
    -0.71
    HKEY
    -0.71
    ッピー
    -0.71
    POSITIVE LOGITS
     Mechanisms
    1.20
    Mechanisms
    1.17
     mechanisms
    1.08
    Mechanism
    0.94
     mechanism
    0.93
     Euros
    0.93
     designers
    0.92
     claust
    0.91
     MSRP
    0.90
     Mechanism
    0.88
    Activations Density 0.024%

    No Known Activations