© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78478
    Prev
    Next
    INDEX
    Explanations

    departments and organizational units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isit
    -0.86
     titel
    -0.82
    opathy
    -0.82
    overse
    -0.81
    ご覧ください
    -0.79
    Mori
    -0.79
    LAHOMA
    -0.75
     GUIDE
    -0.75
    两者
    -0.75
     ANGEL
    -0.75
    POSITIVE LOGITS
     department
    1.22
     Department
    1.08
     LLC
    1.04
     branch
    0.98
     departments
    0.97
     boarding
    0.94
     Centre
    0.94
     مركز
    0.90
     center
    0.90
     "
    0.90
    Activations Density 0.019%

    No Known Activations