© 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. 41-GEMMASCOPE-2-RES-262K
    7. 4303
    Prev
    Next
    INDEX
    Explanations

    particle physics, CERN, LHC

    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
    तुरंग
    0.56
    triangleq
    0.52
     alterações
    0.51
     assumptive
    0.51
     पोषक
    0.50
    TxtArea
    0.50
     ब्लूटूथ
    0.50
    劣
    0.49
    ार्मिक
    0.48
    eterminate
    0.48
    POSITIVE LOGITS
     CERN
    1.52
     LHC
    1.24
     Particle
    1.08
     hadron
    1.05
     GeV
    1.03
     neutrino
    1.02
    Particle
    0.99
     Collider
    0.98
     particle
    0.96
     hadrons
    0.95
    Activations Density 0.008%

    No Known Activations