© 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. 58991
    Prev
    Next
    INDEX
    Explanations

    thousands digit

    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
    θει
    -0.98
     Knowing
    -0.81
     issues
    -0.77
    werpen
    -0.76
    prilis
    -0.74
     inicial
    -0.74
    culada
    -0.73
     enclosures
    -0.72
     reckless
    -0.71
    霈
    -0.71
    POSITIVE LOGITS
    ).\\
    0.90
     также
    0.87
     également
    0.87
     レース
    0.85
    <tr>
    0.83
    verlust
    0.80
    JLabel
    0.79
    ïse
    0.79
     \\
    0.77
     существует
    0.77
    Activations Density 0.005%

    No Known Activations