© 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. 235
    Prev
    Next
    INDEX
    Explanations

    information and explanations

    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
     plenamente
    -1.11
    凪
    -1.11
    作为一个
    -1.10
    焦虑
    -1.07
     fête
    -1.05
     белом
    -1.03
     mivel
    -1.03
    ковым
    -1.03
     következő
    -1.01
    ikusbot
    -1.00
    POSITIVE LOGITS
    Reak
    1.32
     vardı
    1.22
     while
    1.16
    itemID
    1.15
    منبع
    1.15
    Vorte
    1.15
    zionali
    1.14
     необходи
    1.12
     görüntüleri
    1.12
     and
    1.10
    Activations Density 0.203%

    No Known Activations