© 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. 7151
    Prev
    Next
    INDEX
    Explanations

    nuclear and atomic bombs

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

    nuclear bomb or physics

    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
    扦
    0.49
     Ceci
    0.43
     চরণ
    0.43
     வாழ்க்க
    0.42
     COMPANIES
    0.42
     පෙර
    0.41
     வாழ்க்கை
    0.41
    乩
    0.40
     Companies
    0.40
     வடிக
    0.40
    POSITIVE LOGITS
     nuclear
    2.36
    nuclear
    2.20
     ядер
    2.14
    Nuclear
    2.08
     Nuclear
    2.05
     nuk
    2.05
     핵
    2.03
     NUCLEAR
    1.99
    核
    1.99
     thermonuclear
    1.92
    Activations Density 0.081%

    No Known Activations