© 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. 129135
    Prev
    Next
    INDEX
    Explanations

    connect via or with

    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
     to
    -2.66
     estaba
    -1.42
     business
    -1.34
     —
    -1.33
     чтобы
    -1.32
     segunda
    -1.32
     ofrece
    -1.30
    {~
    -1.29
     k
    -1.28
     long
    -1.28
    POSITIVE LOGITS
     decât
    1.49
     chapeau
    1.47
     图案
    1.47
     fără
    1.46
    鷙
    1.41
    årige
    1.39
    
    1.39
     voyager
    1.38
     cwt
    1.35
    Palabras
    1.34
    Activations Density 0.226%

    No Known Activations