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. 8314
    Prev
    Next
    INDEX
    Explanations

    eating

    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
    TextSpan
    -0.82
    ICT
    -0.82
    agem
    -0.73
    灞
    -0.72
    Cpp
    -0.71
     AST
    -0.71
    лади
    -0.71
     Karriere
    -0.70
     zes
    -0.70
    Jo
    -0.70
    POSITIVE LOGITS
     eats
    2.77
     eating
    2.56
     eat
    2.53
     eaten
    2.17
    eating
    2.02
     Eating
    1.98
     cannibal
    1.96
    eat
    1.92
    eats
    1.88
    吃
    1.84
    Activations Density 0.056%

    No Known Activations