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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 33531
    Prev
    Next
    INDEX
    Explanations

    controlled fusion reactor

    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_all/layer_41_width_262k_l0_big
    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
    绞
    0.44
     physiologically
    0.43
     reconfiguration
    0.40
     komplik
    0.40
    LOADING
    0.40
    饲
    0.38
     やっぱり
    0.38
    wearing
    0.37
     формирование
    0.37
    刄
    0.37
    POSITIVE LOGITS
     Fusion
    0.80
     fusion
    0.79
     reactor
    0.78
    Fusion
    0.74
    fusion
    0.70
     Reactor
    0.70
     nuclear
    0.70
     reactors
    0.68
     Nuclear
    0.65
    Nuclear
    0.63
    Activations Density 0.006%

    No Known Activations