© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 123847
    Prev
    Next
    INDEX
    Explanations

    difficult times

    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
     作り方
    -1.45
    -1.41
    欝
    -1.41
    小孩
    -1.37
     confound
    -1.35
    谖
    -1.32
    qtt
    -1.31
     why
    -1.31
    providing
    -1.29
    小孩子
    -1.27
    POSITIVE LOGITS
     posled
    1.32
     estos
    1.30
     nią
    1.27
     exactamente
    1.25
    時期
    1.23
     Different
    1.22
     scheinen
    1.22
     $
    1.22
     годах
    1.20
     etwas
    1.19
    Activations Density 0.035%

    No Known Activations