© 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. 90370
    Prev
    Next
    INDEX
    Explanations

    word endings

    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
     and
    -2.41
    asties
    -1.87
     will
    -1.80
     These
    -1.73
    」、「
    -1.71
     did
    -1.66
     with
    -1.61
     began
    -1.59
     Júnior
    -1.57
    pography
    -1.55
    POSITIVE LOGITS
     estadounid
    2.11
     miniaturka
    2.09
     dobry
    2.05
    
    2.02
     its
    2.02
     quí
    1.99
    傒
    1.98
    婠
    1.96
     rése
    1.92
    鳚
    1.91
    Activations Density 0.471%

    No Known Activations