© 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. 11040
    Prev
    Next
    INDEX
    Explanations

    helping people or solving problems

    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
     habido
    -2.56
    gencias
    -2.50
    requipa
    -2.48
    人の
    -2.44
    breviations
    -2.38
     jest
    -2.38
     personer
    -2.38
     erbjuder
    -2.38
    '
    -2.36
    ඥ
    -2.36
    POSITIVE LOGITS
     Subsequently
    2.98
     Technically
    2.92
     Rather
    2.92
    0
    2.91
     Roughly
    2.91
     Therefore
    2.88
     the
    2.84
     Thus
    2.78
     Somewhat
    2.69
     Ultimately
    2.67
    Activations Density 0.003%

    No Known Activations