© 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-16K
    7. 12060
    Prev
    Next
    INDEX
    Explanations

    anatomical structures and regions

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

    accounting terms and anatomy

    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_16k_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
    風險
    0.48
    Zimbabwe
    0.45
    ᙱ
    0.44
     투자
    0.44
    リスク
    0.44
    motiv
    0.43
    风险
    0.43
     이슈
    0.42
     फंडिंग
    0.42
     মিটিং
    0.42
    POSITIVE LOGITS
     Anatom
    0.52
     Lymph
    0.50
     recl
    0.49
     cerebrospinal
    0.45
    颅
    0.44
     regiones
    0.43
     anatomical
    0.43
     uncommon
    0.43
     cranial
    0.42
     carcinomas
    0.42
    Activations Density 0.034%

    No Known Activations