© 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. 102436
    Prev
    Next
    INDEX
    Explanations

    balance and changes

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires strongly on the change-log action words (removed, merged, added, changed, etc.) that enumerate edits in a revision summary.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     السياس
    -1.12
     complémentaires
    -0.91
    евна
    -0.91
     utilisés
    -0.91
    culas
    -0.88
    
    -0.86
     élevés
    -0.86
     menggunakan
    -0.85
    ván
    -0.85
    εκ
    -0.85
    POSITIVE LOGITS
     changes
    1.62
     balancing
    1.48
     balance
    1.47
     decrease
    1.34
     redesign
    1.30
     design
    1.30
     balanced
    1.27
    nerf
    1.26
     change
    1.26
     increase
    1.22
    Activations Density 0.017%

    No Known Activations