© 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. 119663
    Prev
    Next
    INDEX
    Explanations

    introducing a concept or action

    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
     HOW
    -1.45
    </td>
    -1.42
    It
    -1.37
    鮠
    -1.36
    ものが
    -1.36
    Сегодня
    -1.36
     решила
    -1.36
     хотите
    -1.34
    Она
    -1.32
    居然
    -1.31
    POSITIVE LOGITS
     a
    1.60
    produzione
    1.55
    और
    1.54
     estómago
    1.54
     his
    1.48
     thier
    1.41
     nebst
    1.41
    følge
    1.41
     pulito
    1.39
     damals
    1.38
    Activations Density 0.087%

    No Known Activations