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. 8127
    Prev
    Next
    INDEX
    Explanations

    state of Illinois and code

    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
     their
    -0.93
     燈
    -0.84
     AGUA
    -0.84
     Medications
    -0.79
    ყ
    -0.79
     Gül
    -0.75
     supremely
    -0.75
     วัด
    -0.75
    父亲
    -0.75
     even
    -0.75
    POSITIVE LOGITS
     Illinois
    1.70
     IL
    1.65
    Illinois
    1.45
    IL
    1.30
     Chicago
    1.21
    íl
    1.14
     interleukin
    1.12
     Il
    1.09
     ___
    1.01
     il
    1.00
    Activations Density 0.004%

    No Known Activations