© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101057
    Prev
    Next
    INDEX
    Explanations

    returning or coming back

    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
    0
    -2.31
     для
    -2.25
    6
    -2.20
     für
    -2.14
     dejamos
    -2.11
    Reak
    -2.11
     对
    -2.09
     allgemeine
    -2.09
     wichtigste
    -2.06
     untuk
    -2.05
    POSITIVE LOGITS
    ’
    2.13
    idered
    1.95
    🛑
    1.92
     scrutin
    1.90
    ，”
    1.88
    𝐇
    1.87
    )…
    1.81
    !!)
    1.80
    های
    1.80
    进程
    1.77
    Activations Density 0.005%

    No Known Activations