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. 37
    Prev
    Next
    INDEX
    Explanations

    names starting with W

    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
    watching
    -0.98
    wrong
    -0.85
    volumes
    -0.85
     została
    -0.81
    whole
    -0.81
    Wrong
    -0.81
    gerakan
    -0.77
    warehouse
    -0.76
    ционер
    -0.73
    ✔
    -0.73
    POSITIVE LOGITS
     wang
    1.35
     w
    1.27
     Wang
    1.27
     WV
    1.26
     wg
    1.22
     WK
    1.20
     WN
    1.17
     W
    1.16
     WB
    1.11
     WJ
    1.11
    Activations Density 0.023%

    No Known Activations