Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 421
    Prev
    Next
    INDEX
    Explanations

    processes and system commands

    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
     pepe
    -3.17
     itſelf
    -3.14
    獁
    -3.13
     daer
    -3.11
    緜
    -3.09
     bieber
    -3.06
     sii
    -3.02
    縂
    -3.02
     castro
    -3.02
    淠
    -2.95
    POSITIVE LOGITS
    
    3.08
    ps
    2.91
     stalwart
    2.86
     unveil
    2.75
    翃
    2.66
     turbulent
    2.64
     tangled
    2.61
     trabajo
    2.58
     unquestion
    2.56
     или
    2.48
    Activations Density 0.013%

    No Known Activations