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. 8677
    Prev
    Next
    INDEX
    Explanations

    hard boiled egg

    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
    hypo
    -0.76
    
    -0.72
    niu
    -0.72
     οικο
    -0.70
     filth
    -0.68
    hiz
    -0.68
    ventus
    -0.67
     Projections
    -0.67
     Kart
    -0.66
     douglas
    -0.66
    POSITIVE LOGITS
     hard
    2.67
    hard
    2.11
     Hard
    2.09
     boiled
    2.06
    Hard
    2.05
    HARD
    1.68
     HARD
    1.59
     eggs
    1.54
    boiled
    1.40
     egg
    1.29
    Activations Density 0.033%

    No Known Activations