© 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. 129452
    Prev
    Next
    INDEX
    Explanations

    names beginning with Jesse or Jessie

    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
    鰱
    -2.77
     gefördert
    -2.75
     použití
    -2.73
    鹇
    -2.70
    AutoresizingMask
    -2.69
     bedeckt
    -2.69
    鸲
    -2.64
    AddTagHelper
    -2.58
    
    -2.58
     činnosti
    -2.50
    POSITIVE LOGITS
    -
    3.19
     Then
    3.11
    ка
    3.06
    "
    2.81
     —
    2.44
    也是
    2.31
    …’
    2.27
    ?’
    2.27
    ↵
    2.19
     Also
    2.16
    Activations Density 0.004%

    No Known Activations