© 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. 10-GEMMASCOPE-RES-131K
    7. 84643
    Prev
    Next
    INDEX
    Explanations

    XML attribute minOccurs

    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_10/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
    When
    -2.42
    ↵↵
    -2.36
    Even
    -2.23
     Almost
    -2.05
     Adding
    -2.05
    Every
    -2.03
    t
    -2.02
    日曜日
    -2.02
    悒
    -2.00
    E
    -1.99
    POSITIVE LOGITS
    GraphicsUnit
    2.66
     momentous
    2.36
    赑
    2.34
    沕
    2.27
     horrifying
    2.27
     breathtaking
    2.23
    にあります
    2.17
    蛲
    2.17
     nuovo
    2.16
     soooo
    2.16
    Activations Density 0.001%

    No Known Activations