© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 76115
    Prev
    Next
    INDEX
    Explanations

    pizza and dough

    np_acts-logits-general · gemini-2.5-flash-lite

    pizza, dough, pizzeria

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     électron
    0.43
    RUN
    0.43
     gesprochen
    0.42
     RUN
    0.42
     electron
    0.40
     cadmium
    0.39
    ឈ្ម
    0.39
    đ
    0.38
    மீ
    0.38
     eletr
    0.38
    POSITIVE LOGITS
     Pizza
    1.01
    🍕
    0.93
    Pizza
    0.92
     pizza
    0.90
    pizza
    0.83
     pizzas
    0.79
     pizzeria
    0.79
     dough
    0.74
     Dough
    0.71
     Yeast
    0.64
    Activations Density 0.076%

    No Known Activations