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. 8182
    Prev
    Next
    INDEX
    Explanations

    CSS properties and counts

    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
     zouden
    -0.66
    بره
    -0.65
     softened
    -0.63
    []):
    -0.62
     Kaisers
    -0.61
     下午
    -0.60
    فاده
    -0.60
    Escrito
    -0.59
    QApplication
    -0.59
     clc
    -0.58
    POSITIVE LOGITS
     упаковке
    0.73
     scandal
    0.69
    CrossOrigin
    0.69
     scandals
    0.68
    borg
    0.67
     CY
    0.67
    źdz
    0.66
    ֶה
    0.65
    inergic
    0.65
    biotics
    0.65
    Activations Density 0.065%

    No Known Activations