© 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. 65290
    Prev
    Next
    INDEX
    Explanations

    biomedical entities and applications

    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
    Blur
    0.45
    ofe
    0.43
    ផ្តល់
    0.42
     Providers
    0.40
    𐰼
    0.40
    र्
    0.40
     स्थानांतर
    0.40
    ⎆
    0.39
    oros
    0.39
     Yokohama
    0.38
    POSITIVE LOGITS
     applications
    0.76
    applications
    0.64
     application
    0.63
    应用
    0.63
    Applications
    0.60
     aplikacji
    0.58
     Applications
    0.58
    アプリケーション
    0.58
     aplikace
    0.57
     aplicaciones
    0.54
    Activations Density 0.001%

    No Known Activations