© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 7514
    Prev
    Next
    INDEX
    Explanations

    champion and champagne

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

    Champ, champion, champs

    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
     opat
    0.41
     احتجاج
    0.41
     inver
    0.40
     Antilles
    0.39
     amén
    0.38
     protesta
    0.38
    坴
    0.38
     ہدایت
    0.38
    それで
    0.38
     Advertising
    0.37
    POSITIVE LOGITS
    ions
    0.70
    nats
    0.58
    🏆
    0.58
    ampions
    0.55
     champ
    0.53
     CHAMP
    0.53
     boxer
    0.53
    agne
    0.52
    Champ
    0.52
    IONS
    0.52
    Activations Density 0.018%

    No Known Activations