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. 179
    Prev
    Next
    INDEX
    Explanations

    said or wrote followed by a colon

    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
     â
    -0.88
    breviations
    -0.83
     অ
    -0.82
    这下
    -0.81
    telé
    -0.81
    edc
    -0.80
     ―
    -0.79
    ḳ
    -0.79
     nicole
    -0.79
    laston
    -0.78
    POSITIVE LOGITS
    :
    1.22
     leeren
    0.97
    avocat
    0.95
    Ингредиенты
    0.92
    deliver
    0.90
     vorhandenen
    0.90
     sayang
    0.89
    said
    0.88
    intéress
    0.88
     ekolog
    0.87
    Activations Density 0.002%

    No Known Activations