© 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. 67374
    Prev
    Next
    INDEX
    Explanations

    Objective-C header imports

    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
    ၟ
    -2.30
    Ꮉ
    -2.05
    無い
    -1.91
    Ꮞ
    -1.80
    ꈊ
    -1.79
    ኧ
    -1.77
    quelize
    -1.74
     vasta
    -1.74
    ᩠
    -1.73
    幸いです
    -1.72
    POSITIVE LOGITS
    źdz
    1.95
    )
    1.87
    He
    1.78
    ks
    1.74
    ">{{
    1.67
    孓
    1.58
    驀
    1.57
    
    1.54
    finds
    1.52
    began
    1.52
    Activations Density 0.007%

    No Known Activations