Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110076
    Prev
    Next
    INDEX
    Explanations

    healthy or unhealthy food

    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
    cule
    -0.91
    Coffee
    -0.79
    izacji
    -0.74
    vul
    -0.73
     intensiv
    -0.72
    Vul
    -0.72
    mechanical
    -0.72
    نان
    -0.72
    coffee
    -0.71
    marginBottom
    -0.71
    POSITIVE LOGITS
     healthy
    4.75
     healthier
    4.28
    healthy
    3.84
     Healthy
    3.63
     health
    3.45
    Healthy
    3.31
     healthful
    3.00
     unhealthy
    2.92
     healthiest
    2.91
     HEALTH
    2.89
    Activations Density 0.059%

    No Known Activations