© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47190
    Prev
    Next
    INDEX
    Explanations

    bonus points

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

    The neuron detects occurrences of “bonus” markers or headings indicating bonus content (e.g. “Bonus,” “Bonus Tracks,” “Bonus points”).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     bonus
    -1.11
     Bonus
    -1.03
     BONUS
    -1.01
    あえて
    -1.00
    素晴
    -0.98
     bonuses
    -0.97
     vriende
    -0.96
    bonus
    -0.94
    BONUS
    -0.93
     búsqueda
    -0.89
    POSITIVE LOGITS
    ses
    1.27
     features
    1.26
    sistors
    1.16
    Features
    1.10
     chapter
    1.09
     points
    1.05
    docs
    1.05
     factor
    1.04
     rounds
    1.02
    es
    1.01
    Activations Density 0.006%

    No Known Activations