© 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. 120907
    Prev
    Next
    INDEX
    Explanations

    medical treatment or concepts

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

    tracking, taxes, meaning, round

    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
    b
    0.49
    Panel
    0.46
     panel
    0.46
     보다
    0.46
     complainant
    0.46
    (%
    0.46
    (
    0.45
              
    0.44
     Roop
    0.43
     holders
    0.43
    POSITIVE LOGITS
     sucede
    0.50
    這些
    0.49
    それぞれ
    0.48
    診療
    0.48
     destino
    0.48
    每個
    0.48
    ικο
    0.47
    各自
    0.46
    治療
    0.46
    ಿಕೆಯ
    0.46
    Activations Density 0.000%

    No Known Activations