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. 155
    Prev
    Next
    INDEX
    Explanations

    software license text

    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
    Siz
    -0.75
     practicar
    -0.73
     soared
    -0.68
    beds
    -0.68
    Trent
    -0.67
     Interrupt
    -0.66
    ณะ
    -0.66
    rua
    -0.65
    Mutagenicity
    -0.65
    ງ
    -0.65
    POSITIVE LOGITS
     Junk
    0.67
     Goes
    0.65
     sprawia
    0.64
    ꒱
    0.64
     wine
    0.63
     Updates
    0.63
     године
    0.62
     connectivity
    0.62
     igual
    0.62
    idata
    0.61
    Activations Density 0.067%

    No Known Activations