© 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. 92576
    Prev
    Next
    INDEX
    Explanations

    scientific fields

    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
     Condo
    -0.84
    ப்
    -0.76
     Boiling
    -0.74
    啷
    -0.74
     Yar
    -0.74
     Kalman
    -0.74
     Charter
    -0.73
     Beagle
    -0.72
    lepaskan
    -0.71
     Wiener
    -0.71
    POSITIVE LOGITS
    Field
    1.32
     Field
    1.20
     ghosts
    1.05
     field
    0.99
     FIELD
    0.99
     corn
    0.96
     鬼
    0.91
     ghost
    0.90
     crop
    0.90
    Ghost
    0.87
    Activations Density 0.009%

    No Known Activations