© 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. 34980
    Prev
    Next
    INDEX
    Explanations

    layer

    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
    shadowRadius
    -1.27
    eroon
    -1.11
     ragaz
    -1.05
     bagay
    -1.04
    锴
    -1.01
    agog
    -1.00
    shadowOpacity
    -0.99
     ,‬
    -0.98
     lèvres
    -0.97
    atonin
    -0.97
    POSITIVE LOGITS
    ered
    1.34
     thickness
    1.22
    ar
    1.22
    ant
    1.20
     Layer
    1.17
     brasileiros
    1.12
    )),
    1.10
     {"
    1.08
     thicknesses
    1.07
    erd
    1.06
    Activations Density 0.021%

    No Known Activations