© 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. 24058
    Prev
    Next
    INDEX
    Explanations

    bolster or buoy

    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
    .
    -2.84
     transformar
    -2.11
    內容簡介
    -2.09
    butuhkan
    -2.08
     Aufenthalt
    -2.06
     They
    -2.02
     combinar
    -2.00
     môže
    -2.00
     But
    -2.00
    蹰
    -1.99
    POSITIVE LOGITS
    .”
    2.50
    1
    2.20
    8
    2.08
     प्रतिशत
    2.06
    4
    2.05
    missão
    2.02
    “
    1.99
    5
    1.98
     stupe
    1.96
     seit
    1.91
    Activations Density 0.007%

    No Known Activations