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. 8549
    Prev
    Next
    INDEX
    Explanations

    cost or costs

    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
    cismo
    -0.81
    aviar
    -0.79
     Cz
    -0.78
    ServletRequest
    -0.75
    chase
    -0.75
    joje
    -0.73
    んでる
    -0.73
    高等学校
    -0.72
     împ
    -0.72
     திரு
    -0.71
    POSITIVE LOGITS
     cost
    2.95
     costs
    2.70
    cost
    2.34
    Cost
    2.16
     weight
    2.11
     weights
    2.02
     Cost
    1.98
    costs
    1.89
     Costs
    1.86
    Costs
    1.86
    Activations Density 0.035%

    No Known Activations