© 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. 10-GEMMASCOPE-RES-131K
    7. 75541
    Prev
    Next
    INDEX
    Explanations

    light colored materials

    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_10/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
     Importantly
    -1.66
    ↵
    -1.52
     ”
    -1.41
    s
    -1.40
     también
    -1.38
     Дру
    -1.33
     Notably
    -1.32
    ti
    -1.30
     Thus
    -1.26
     også
    -1.26
    POSITIVE LOGITS
     light
    1.84
     Light
    1.73
    light
    1.64
     lightest
    1.58
     مناطق
    1.55
    Gén
    1.53
     轻
    1.43
     Lighter
    1.39
     lighter
    1.39
    urtstag
    1.37
    Activations Density 0.050%

    No Known Activations