© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 197408
    Prev
    Next
    INDEX
    Explanations

    complement, antigen, first, monocytes

    np_acts-logits-general · gemini-2.5-flash-lite

    business glossary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     worry
    0.65
    غ
    0.53
     workman
    0.46
    v
    0.46
     zoon
    0.46
     Worry
    0.43
     fundament
    0.43
     worldly
    0.43
    gh
    0.42
     torment
    0.42
    POSITIVE LOGITS
    ವಾಗಿರುತ್ತದೆ
    0.52
     ಎರ
    0.52
    🧶
    0.51
    👐
    0.50
    த்திலிருந்து
    0.50
    ectl
    0.49
    🕋
    0.47
    ǎng
    0.47
    ‍♂
    0.47
     বিকল্প
    0.46
    Activations Density 0.002%

    No Known Activations