© 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. 112534
    Prev
    Next
    INDEX
    Explanations

    amount of

    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
    
    -1.78
    Menurut
    -1.66
    圌
    -1.63
    Sebelumnya
    -1.62
    摹
    -1.59
    那我
    -1.59
    珦
    -1.59
     nación
    -1.58
     orígenes
    -1.58
    .'”
    -1.55
    POSITIVE LOGITS
     fisico
    1.66
     Their
    1.66
    灕
    1.62
     betrieb
    1.54
    荅
    1.52
    nými
    1.52
     sebagainya
    1.52
     pervasive
    1.48
     Them
    1.45
    的头
    1.40
    Activations Density 0.005%

    No Known Activations