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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8508
    Prev
    Next
    INDEX
    Explanations

    song titles and album names

    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
    REME
    -0.97
     ۲۰۱
    -0.93
    idenza
    -0.88
    icolon
    -0.87
     febr
    -0.85
    ीडियो
    -0.83
     независи
    -0.82
    emang
    -0.81
     couvert
    -0.80
    🥍
    -0.80
    POSITIVE LOGITS
     Yr
    1.06
     yr
    0.88
    Yr
    0.88
    Vlastnosti
    0.85
    ʦ
    0.85
    运算
    0.84
    Satan
    0.83
     getMessage
    0.83
    的区别
    0.82
     통해
    0.80
    Activations Density 0.068%

    No Known Activations