© 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. 34-GEMMASCOPE-RES-131K
    4. 103106
    Prev
    Next
    INDEX
    Explanations

    competitions at sports events

    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_34/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
    /*
    -1.20
     /*
    -1.17
    http
    -0.87
     größten
    -0.84
    \\
    -0.84
    https
    -0.82
    ❉
    -0.81
     $
    -0.78
    /*
    
    -0.77
     i
    -0.77
    POSITIVE LOGITS
    <b>
    2.66
    <strong>
    2.61
    mathbf
    1.91
     **
    1.52
    textbf
    1.30
     '''
    1.27
    ӈ
    1.03
    ЦИИ
    0.97
     Nieuws
    0.96
     '**
    0.95
    Activations Density 0.114%

    No Known Activations