© 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. 44578
    Prev
    Next
    INDEX
    Explanations

    program code snippets

    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
    ⚋
    -2.67
    ೣ
    -2.55
    المل
    -2.33
    ꦁ
    -2.27
    ༈
    -2.17
    责编
    -2.16
    L
    -2.06
     државе
    -2.05
     作り方
    -2.03
    
    -2.03
    POSITIVE LOGITS
    t
    3.02
    '
    2.41
     nasceu
    2.03
    ва
    1.97
     permiten
    1.93
     accommodates
    1.88
     “
    1.87
    x
    1.86
    .
    1.86
    (?)
    1.84
    Activations Density 0.001%

    No Known Activations