© 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. 34-GEMMASCOPE-RES-131K
    7. 65636
    Prev
    Next
    INDEX
    Explanations

    distances, fractions, and miles

    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_34/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
    Sixty
    -1.05
     Sixty
    -0.96
    Forty
    -0.91
    Thirty
    -0.84
    Replies
    -0.83
    thirty
    -0.82
     Behav
    -0.81
     Forty
    -0.81
    žek
    -0.81
    oug
    -0.81
    POSITIVE LOGITS
     mile
    2.22
     ½
    1.85
     five
    1.56
     ¾
    1.54
     half
    1.54
    ½
    1.52
     ¼
    1.50
     quarter
    1.39
    mile
    1.38
     seven
    1.29
    Activations Density 0.052%

    No Known Activations