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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 8695
    Prev
    Next
    INDEX
    Explanations

    nuclear energy and related topics

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

    nuclear reactor

    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_40_width_16k_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
     ricon
    0.43
    尴尬
    0.43
     Alias
    0.42
     Ambulance
    0.42
    鸦
    0.41
    Dragging
    0.41
    营销
    0.40
    填写
    0.40
    轿
    0.40
     Gay
    0.40
    POSITIVE LOGITS
     nuclear
    2.16
     Nuclear
    2.08
     reactor
    2.03
    nuclear
    2.00
     IAEA
    1.98
    Nuclear
    1.97
     NUCLEAR
    1.95
     plutonium
    1.84
     uranium
    1.83
    NUCLEAR
    1.82
    Activations Density 0.129%

    No Known Activations