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. 8264
    Prev
    Next
    INDEX
    Explanations

    study, logistics, acting, evaluation

    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
    jag
    -0.73
    ո
    -0.72
     filing
    -0.69
     obud
    -0.68
     öfter
    -0.68
     мають
    -0.68
     MSRP
    -0.68
    VIA
    -0.68
    Pins
    -0.67
    licans
    -0.67
    POSITIVE LOGITS
     Stratton
    0.97
    صاص
    0.83
    LEn
    0.82
     Vass
    0.80
     operations
    0.79
    한국
    0.79
     lastName
    0.78
    eliner
    0.78
     operational
    0.77
    шу
    0.75
    Activations Density 0.013%

    No Known Activations