© 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. 16-GEMMASCOPE-2-RES-262K
    7. 20649
    Prev
    Next
    INDEX
    Explanations

    fighter jets and aircraft

    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_16_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
    work
    0.53
    POR
    0.51
    वर्क
    0.51
    𝐝
    0.50
    筱
    0.50
    чай
    0.49
    Shower
    0.49
    🥔
    0.49
    𝙜
    0.49
     ಸುಬ್ಬ
    0.48
    POSITIVE LOGITS
     aircraft
    0.81
     aviones
    0.79
     squadrons
    0.65
     MiG
    0.64
     airplanes
    0.64
     sechs
    0.60
     दोन
    0.60
     Lockheed
    0.59
     helicopters
    0.57
     pesawat
    0.57
    Activations Density 0.023%

    No Known Activations