© 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. 86930
    Prev
    Next
    INDEX
    Explanations

    mas preceded by words like ti, pi, te

    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
     trasero
    -2.55
     ſever
    -2.53
    腚
    -2.50
     diarios
    -2.48
     sustains
    -2.41
     dévelo
    -2.30
     を
    -2.30
     любого
    -2.28
     eines
    -2.27
     añadido
    -2.27
    POSITIVE LOGITS
    劻
    2.52
    ༵
    2.47
     twor
    2.42
    óstico
    2.30
    {
    2.25
    釭
    2.14
    这些
    2.11
    鍇
    2.09
     exacting
    2.09
     nouveau
    2.09
    Activations Density 0.017%

    No Known Activations