© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 2120
    Prev
    Next
    INDEX
    Explanations

    meat and meals

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

    food items and dishes

    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_53_width_65k_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
     heredit
    0.44
     माननीय
    0.44
     luminance
    0.44
     परस्मैपदी
    0.43
     आवासीय
    0.43
    🏗
    0.42
    ഭ്യാസ
    0.41
    宦
    0.41
    🏭
    0.41
     compositional
    0.40
    POSITIVE LOGITS
     chicken
    1.95
     steak
    1.93
     meatballs
    1.93
     pork
    1.84
     pasta
    1.83
     steaks
    1.83
     sausages
    1.82
     burgers
    1.79
     grilled
    1.78
     hamburgers
    1.78
    Activations Density 0.929%

    No Known Activations