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. 8603
    Prev
    Next
    INDEX
    Explanations

    dogs, breeds, and numbers

    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
     rescues
    -1.20
     rescu
    -1.06
     rescue
    -1.05
     exo
    -1.00
     Exotic
    -0.94
     یون
    -0.94
    rescue
    -0.91
     rescued
    -0.90
     enrichment
    -0.88
    ixel
    -0.85
    POSITIVE LOGITS
     dog
    1.59
    dog
    1.27
     DOG
    1.26
    狗
    1.20
     dogs
    1.19
    Dog
    1.13
     Dog
    1.11
     canine
    1.09
     Dogs
    1.09
     köpek
    1.07
    Activations Density 0.061%

    No Known Activations