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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 184
    Prev
    Next
    INDEX
    Explanations

    managing, catching, playing, coughing, finding

    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
     need
    -1.36
    ouncement
    -1.30
    alakip
    -1.29
     will
    -1.28
    tieron
    -1.28
     古着
    -1.25
     way
    -1.23
     possible
    -1.23
     victorious
    -1.22
     فبراير
    -1.20
    POSITIVE LOGITS
     being
    2.17
     having
    1.57
     proactively
    1.53
    ኵ
    1.38
     orchestr
    1.36
     zrobić
    1.35
     finding
    1.34
    acheteur
    1.33
     kupić
    1.33
    我的
    1.33
    Activations Density 0.355%

    No Known Activations