© 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. 47699
    Prev
    Next
    INDEX
    Explanations

    range, duration, or scope

    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
    .
    -2.41
     distinguir
    -2.23
    躋
    -2.00
     animado
    -1.91
     Abweich
    -1.90
     vektör
    -1.80
     optimizar
    -1.80
     nemoc
    -1.80
    一首
    -1.79
     ДА
    -1.79
    POSITIVE LOGITS
    e
    2.52
    潆
    2.41
    臯
    2.38
    ︓
    2.36
    h
    2.20
    呜呜
    2.08
    气氛
    2.06
    䊐
    2.05
    普通的
    2.03
    栻
    2.00
    Activations Density 0.017%

    No Known Activations