© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 1185
    Prev
    Next
    INDEX
    Explanations

    hydrogen and oxygen ions

    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
    ្នាំ
    0.63
    জ্জনক
    0.57
    ួក
    0.56
    arranty
    0.55
     élytres
    0.54
    ួរ
    0.54
    <unused973>
    0.54
    <unused671>
    0.53
     മിക
    0.53
    ាតុ
    0.52
    POSITIVE LOGITS
     Hydrogen
    0.86
     hydrogen
    0.82
     ions
    0.80
     protons
    0.77
     H
    0.72
    Hydrogen
    0.70
     cations
    0.69
     Oxygen
    0.68
     hydrogens
    0.67
     proton
    0.66
    Activations Density 0.053%

    No Known Activations