© 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. 81611
    Prev
    Next
    INDEX
    Explanations

    tect/tec + suffix

    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
     Conti
    -0.86
     Format
    -0.79
     format
    -0.78
     tach
    -0.75
     формат
    -0.75
    好久
    -0.74
     freight
    -0.73
     ace
    -0.72
    format
    -0.72
    ня
    -0.71
    POSITIVE LOGITS
     apprécié
    0.90
    nique
    0.86
    nival
    0.79
    живать
    0.78
    ジット
    0.77
    estival
    0.77
     acheté
    0.77
     interessa
    0.76
    την
    0.76
     слоя
    0.76
    Activations Density 0.013%

    No Known Activations