© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 45682
    Prev
    Next
    INDEX
    Explanations

    online discussion boards

    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
    Balk
    -0.75
    Juri
    -0.71
    BLK
    -0.70
     المه
    -0.69
     dilated
    -0.68
     Hern
    -0.66
     spina
    -0.66
    Glob
    -0.66
    recated
    -0.65
    alition
    -0.64
    POSITIVE LOGITS
     boards
    2.41
     board
    1.94
    boards
    1.91
     Boards
    1.87
     message
    1.79
    Boards
    1.72
     Message
    1.70
    Message
    1.52
    message
    1.51
     Board
    1.49
    Activations Density 0.031%

    No Known Activations