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. 192
    Prev
    Next
    INDEX
    Explanations

    electricity supply and prices

    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
     Valentines
    -1.02
     valentine
    -0.94
    男朋友
    -0.94
     audiobook
    -0.91
     exodus
    -0.90
     penguin
    -0.89
    compte
    -0.88
     reces
    -0.88
     Manchuria
    -0.88
     dumbbell
    -0.88
    POSITIVE LOGITS
     generation
    1.47
     supply
    1.25
     provider
    1.23
     generating
    1.18
     consumption
    1.17
     generated
    1.15
     usage
    1.09
     transmission
    1.05
     generators
    1.04
    供应
    1.04
    Activations Density 0.021%

    No Known Activations