© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 994
    Prev
    Next
    INDEX
    Explanations

    aircraft, engine, flight, safety

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ꫝ
    0.50
    潋
    0.48
     κοινων
    0.45
     부동산
    0.45
     absur
    0.44
     dystopian
    0.43
     दलित
    0.43
    纺
    0.43
     সাম্প্রদায়িক
    0.42
     じゃん
    0.42
    POSITIVE LOGITS
     aircraft
    1.92
    Aircraft
    1.80
     Aircraft
    1.74
     aviation
    1.70
    aircraft
    1.63
    飛行
    1.58
     flight
    1.57
     aeron
    1.55
    航空
    1.52
     авиа
    1.52
    Activations Density 0.115%

    No Known Activations