© 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. 129082
    Prev
    Next
    INDEX
    Explanations

    Chris and names

    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
    ↵
    -3.72
    the
    -3.14
     erfolgreichen
    -3.03
     
    -2.88
     heisst
    -2.75
    </strong>
    -2.73
    ৢ
    -2.61
     we
    -2.50
     .
    -2.48
     beschäf
    -2.45
    POSITIVE LOGITS
     {
    3.16
    芣
    3.06
     eder
    2.77
    笮
    2.75
    erintah
    2.70
     може
    2.70
     italiane
    2.66
     aprire
    2.53
    勠
    2.53
     koke
    2.52
    Activations Density 0.004%

    No Known Activations