© 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. 82936
    Prev
    Next
    INDEX
    Explanations

    Growth factors, influence, fast download

    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
     cold
    -1.13
    冷
    -0.93
    Cold
    -0.91
    Chinese
    -0.77
    cold
    -0.75
    óbal
    -0.75
     Cold
    -0.74
    NW
    -0.73
     Northwest
    -0.71
    拜
    -0.71
    POSITIVE LOGITS
     Iroquois
    1.20
     Mohawk
    1.09
     SUNY
    1.02
    Syracuse
    1.00
     Syracuse
    0.99
    Niagara
    0.99
     Niagara
    0.90
     Genesee
    0.89
     Buffalo
    0.87
     nations
    0.85
    Activations Density 0.012%

    No Known Activations