© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 54825
    Prev
    Next
    INDEX
    Explanations

    nuclear fusion

    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_65k_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
    ϡ
    0.44
     sorption
    0.43
    Chocolate
    0.40
    chocolate
    0.40
     carbonyl
    0.39
     physico
    0.39
     spectral
    0.39
    ASCADE
    0.38
    財
    0.38
     punctual
    0.38
    POSITIVE LOGITS
     fusing
    0.70
     fuses
    0.63
     fusion
    0.61
    融合
    0.60
     fuse
    0.58
    Fusion
    0.57
     fused
    0.57
     Fusion
    0.55
     fusible
    0.54
     fusión
    0.51
    Activations Density 0.046%

    No Known Activations