Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110344
    Prev
    Next
    INDEX
    Explanations

    must present

    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
     cooking
    -0.84
    ◟
    -0.78
     febbraio
    -0.75
     род
    -0.72
     giugno
    -0.69
     članak
    -0.69
    cumin
    -0.69
     Leinwand
    -0.69
     от
    -0.68
    icace
    -0.68
    POSITIVE LOGITS
    Mats
    0.98
     مواد
    0.88
     Mats
    0.88
     سل
    0.88
    低于
    0.86
     undisputed
    0.85
    Resolver
    0.84
    moving
    0.84
     resolver
    0.83
     mov
    0.83
    Activations Density 0.038%

    No Known Activations