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. 7970
    Prev
    Next
    INDEX
    Explanations

    numbers and counting

    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
    iniest
    -0.85
     fifty
    -0.82
    addParameter
    -0.81
     sixty
    -0.81
     feces
    -0.78
     eighty
    -0.78
    audrait
    -0.78
    Akhir
    -0.77
    Deel
    -0.77
     thirty
    -0.76
    POSITIVE LOGITS
    一二
    2.00
    ABC
    1.48
     ABC
    1.45
     abc
    1.37
     १
    1.34
    numbers
    1.34
     ۱
    1.25
    ABCDEF
    1.24
    Numbers
    1.23
    1
    1.21
    Activations Density 0.104%

    No Known Activations