© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 87240
    Prev
    Next
    INDEX
    Explanations

    code comments and headers

    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
     }}{\
    -0.84
    mme
    -0.81
    reiro
    -0.81
    "/>
    -0.80
    anged
    -0.78
    inoco
    -0.77
    ']/
    -0.74
    </h2>
    -0.74
    rul
    -0.73
     baie
    -0.72
    POSITIVE LOGITS
    <h3>
    1.52
    cadeira
    0.81
     seem
    0.79
    modelo
    0.73
    BI
    0.73
    xF
    0.73
    шое
    0.73
    语文
    0.71
     ●
    0.71
     seems
    0.71
    Activations Density 0.010%

    No Known Activations