© 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. 41897
    Prev
    Next
    INDEX
    Explanations

    addressing "you" directly

    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
    -2.11
     และ
    -1.91
     également
    -1.77
    particularly
    -1.73
     horrid
    -1.70
     এবং
    -1.69
    somewhat
    -1.64
    และ
    -1.59
    especially
    -1.57
     също
    -1.54
    POSITIVE LOGITS
     any
    1.84
     there
    1.70
     good
    1.66
     getting
    1.63
     better
    1.61
     increases
    1.61
     new
    1.60
     noteworthy
    1.59
     difficulties
    1.59
     facilitates
    1.55
    Activations Density 0.013%

    No Known Activations