© 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. 10-GEMMASCOPE-RES-131K
    4. 130951
    Prev
    Next
    INDEX
    Explanations

    creation date

    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
    \
    -3.73
    妧
    -2.61
     carlo
    -2.53
    鹛
    -2.45
    笆
    -2.42
    を
    -2.42
    setLong
    -2.36
    锘
    -2.36
    佧
    -2.30
     TICKETS
    -2.28
    POSITIVE LOGITS
     neuem
    3.03
     The
    2.72
     irgende
    2.58
     quintessential
    2.56
    杙
    2.55
    o
    2.53
    想
    2.47
     comical
    2.41
     Gutes
    2.41
     certainement
    2.39
    Activations Density 0.010%

    No Known Activations