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. 8509
    Prev
    Next
    INDEX
    Explanations

    Chrysler, Robot, Archive, Q:

    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
     строи
    -0.86
    coders
    -0.81
     disco
    -0.79
    发现
    -0.78
    發現
    -0.78
    hikari
    -0.76
    ESPN
    -0.75
    atti
    -0.74
     LCD
    -0.73
    bourg
    -0.70
    POSITIVE LOGITS
     Hydra
    0.75
    的多
    0.75
     podmín
    0.72
     Stream
    0.72
    olanda
    0.69
    朐
    0.69
     هول
    0.69
    FilterChain
    0.68
    FFIC
    0.67
     Druid
    0.67
    Activations Density 0.018%

    No Known Activations