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. 8132
    Prev
    Next
    INDEX
    Explanations

    X-UA-Compatible

    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
    があり
    -1.66
    や
    -1.65
    を
    -1.59
    などは
    -1.55
    がある
    -1.51
    がありますが
    -1.48
    前は
    -1.45
    などが
    -1.45
     which
    -1.45
     both
    -1.43
    POSITIVE LOGITS
    為に
    1.96
    様な
    1.52
    ところに
    1.46
    で見る
    1.46
    に入れる
    1.40
    つづく
    1.38
    感じです
    1.36
    の方に
    1.33
    におすすめ
    1.31
     atento
    1.25
    Activations Density 0.018%

    No Known Activations