© 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. 59114
    Prev
    Next
    INDEX
    Explanations

    names and surnames

    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
     fluido
    -0.90
     crashing
    -0.86
     muối
    -0.83
    vä
    -0.79
    ORF
    -0.79
    ρα
    -0.79
    hér
    -0.78
     Saviour
    -0.77
     paff
    -0.76
     pourrais
    -0.76
    POSITIVE LOGITS
    续
    0.77
     aproximada
    0.75
    </code>
    0.71
     kurang
    0.71
    纷纷
    0.69
    ₆
    0.69
    ís
    0.69
    惘
    0.68
     czu
    0.68
     dés
    0.67
    Activations Density 0.114%

    No Known Activations