© 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. 37984
    Prev
    Next
    INDEX
    Explanations

    Medicine or medical terms

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

    treats his/me

    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
     ресур
    0.47
     funzione
    0.45
     discouraging
    0.45
     crescita
    0.44
     параметр
    0.43
    ัตว์
    0.43
    <0xBB>
    0.42
    𝒂
    0.42
     americ
    0.41
    λικ
    0.41
    POSITIVE LOGITS
    舊
    0.52
    旧
    0.51
     旧
    0.50
    ступи
    0.47
    小小
    0.47
     installments
    0.46
    namespaces
    0.46
    เก่า
    0.45
    τη
    0.44
     svých
    0.44
    Activations Density 0.000%

    No Known Activations