© 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. 57300
    Prev
    Next
    INDEX
    Explanations

    Helium and helium-3

    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
    Bul
    0.42
    ウド
    0.40
    aver
    0.38
     Bul
    0.38
    铆
    0.37
    TOKEN
    0.37
     Dign
    0.36
    folding
    0.36
    ห้อง
    0.36
    有害
    0.36
    POSITIVE LOGITS
     helium
    0.91
     Helium
    0.89
    helium
    0.81
     superfluid
    0.81
    氦
    0.77
    헬
    0.61
     heli
    0.61
    Hel
    0.58
     HEL
    0.57
     hel
    0.57
    Activations Density 0.003%

    No Known Activations