© 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. 111424
    Prev
    Next
    INDEX
    Explanations

    simply just

    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
     ここ
    -1.95
     Their
    -1.83
    le
    -1.70
    鈈
    -1.57
    邻居
    -1.52
     cambian
    -1.52
     realizando
    -1.47
     independente
    -1.45
    h
    -1.44
     belki
    -1.43
    POSITIVE LOGITS
    onavir
    1.69
     had
    1.64
     received
    1.62
     повітря
    1.59
     includes
    1.59
    存于互联网档案馆
    1.59
    
    1.59
    嬪
    1.58
    ׇ
    1.54
    fertigt
    1.53
    Activations Density 0.004%

    No Known Activations