© 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. 12139
    Prev
    Next
    INDEX
    Explanations

    desire and desires

    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
    O
    -3.30
     để
    -3.17
    N
    -2.73
     своё
    -2.69
     dà
    -2.58
    푆
    -2.58
    をご覧
    -2.52
     sape
    -2.50
    ."
    -2.48
    眎
    -2.42
    POSITIVE LOGITS
     That
    2.52
    ↵↵
    2.45
     trabajar
    2.34
    that
    2.31
    ÇÕES
    2.27
    .
    2.25
     که
    2.17
    Eglise
    2.17
     pusieron
    2.14
    籐
    2.14
    Activations Density 0.010%

    No Known Activations