© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77037
    Prev
    Next
    INDEX
    Explanations

    dense concepts

    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
     blessed
    -1.01
     Entstehung
    -0.88
     Vorgang
    -0.88
     Blessed
    -0.85
    DateFormatter
    -0.79
     Fähigkeit
    -0.77
    лючение
    -0.77
    .].
    -0.77
     gesam
    -0.76
     Perception
    -0.75
    POSITIVE LOGITS
     packed
    1.14
    packed
    1.08
     packing
    1.05
     populated
    1.02
    ly
    0.90
    fog
    0.86
     array
    0.85
    REUTERS
    0.84
     populate
    0.84
    垦
    0.84
    Activations Density 0.024%

    No Known Activations