© 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. 60119
    Prev
    Next
    INDEX
    Explanations

    priority areas

    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
    Mask
    -0.80
     Outreach
    -0.74
     Casanova
    -0.74
    ABLES
    -0.73
     fVar
    -0.72
     Lucknow
    -0.71
     FTX
    -0.71
    Bas
    -0.71
    ADAS
    -0.71
     invariance
    -0.71
    POSITIVE LOGITS
    recipient
    0.85
     recipient
    0.82
     aid
    0.80
    exits
    0.77
     reformers
    0.75
     ownership
    0.75
    Gps
    0.74
     tracking
    0.74
     harmon
    0.73
     tied
    0.71
    Activations Density 0.019%

    No Known Activations