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. 8358
    Prev
    Next
    INDEX
    Explanations

    not numbers

    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
    вих
    -0.78
     infos
    -0.78
    ProgressHUD
    -0.76
     OY
    -0.75
    тным
    -0.74
    marginBottom
    -0.73
     mongodb
    -0.73
    🈹
    -0.73
    SharedDtor
    -0.73
     pgs
    -0.72
    POSITIVE LOGITS
     numbers
    3.92
    numbers
    3.09
     Numbers
    3.08
    Numbers
    2.91
     numeric
    2.70
    数字
    2.69
     números
    2.64
     NUMBERS
    2.61
     numerals
    2.58
     digits
    2.52
    Activations Density 0.201%

    No Known Activations