© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 105757
    Prev
    Next
    INDEX
    Explanations

    names like Michael and Michigan

    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
     When
    -1.97
     If
    -1.94
     
    -1.71
     According
    -1.65
     Before
    -1.63
     In
    -1.62
     T
    -1.62
     Because
    -1.56
    <i>
    -1.55
     With
    -1.49
    POSITIVE LOGITS
    齜
    2.09
    andering
    2.05
     bluz
    1.90
    ांकि
    1.90
    眎
    1.85
     noirs
    1.84
    
    1.83
    苼
    1.82
     ideje
    1.77
     favoritas
    1.74
    Activations Density 0.047%

    No Known Activations