Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 328
    Prev
    Next
    INDEX
    Explanations

    diameter and units

    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
     it
    -1.73
     Además
    -1.72
    </h5>
    -1.71
    ;
    
    -1.70
    there
    -1.69
     也
    -1.64
     Also
    -1.62
    也
    -1.57
    _
    -1.57
     Mientras
    -1.56
    POSITIVE LOGITS
    짭
    1.63
    Diameter
    1.61
     作り方
    1.57
     adalah
    1.55
    SaveChangesAsync
    1.53
     ساعد
    1.53
    Beskrivning
    1.52
    樁
    1.51
    América
    1.49
     เปิด
    1.49
    Activations Density 0.027%

    No Known Activations