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. 64
    Prev
    Next
    INDEX
    Explanations

    but overall

    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
     bahkan
    -1.16
    mathrm
    -1.03
    ただの
    -0.93
    そこに
    -0.93
    来看看
    -0.92
    今でも
    -0.91
    ꈍ
    -0.91
     verschied
    -0.91
     écoulé
    -0.90
     nämlich
    -0.90
    POSITIVE LOGITS
     overall
    7.31
    Overall
    5.94
     Overall
    5.59
    overall
    5.19
    整体
    3.67
    OVERALL
    3.63
    总体
    3.63
     insgesamt
    3.44
    整體
    3.41
     all
    3.33
    Activations Density 0.031%

    No Known Activations