© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 95608
    Prev
    Next
    INDEX
    Explanations

    programming commands followed by technical terms

    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_22/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
    лтемелер
    -1.20
    mousse
    -1.20
    ࣭
    -1.19
    camis
    -1.19
    colos
    -1.19
    logne
    -1.16
    krish
    -1.16
    localisation
    -1.16
    kanı
    -1.15
    whal
    -1.15
    POSITIVE LOGITS
    ()
    1.28
    termilk
    1.21
    ich
    1.15
    l
    1.13
    داً
    1.13
    😊
    1.12
    \_
    1.12
    了一個
    1.10
     associated
    1.09
    el
    1.08
    Activations Density 0.110%

    No Known Activations