© 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. 127379
    Prev
    Next
    INDEX
    Explanations

    date and time conversion

    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
    ↵↵
    -2.19
    )
    -1.57
    {
    -1.49
    за
    -1.48
    ital
    -1.41
     که
    -1.35
     douche
    -1.35
    вести
    -1.33
     heuti
    -1.33
    водить
    -1.32
    POSITIVE LOGITS
     ''
    1.65
     akar
    1.65
     mencionados
    1.59
     akad
    1.58
    ⃙
    1.45
     from
    1.42
    \
    1.41
     pensado
    1.39
    actionMode
    1.39
     "
    1.39
    Activations Density 0.011%

    No Known Activations