© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31940
    Prev
    Next
    INDEX
    Explanations

    crossover and recombination

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

    references to cross-media content, particularly related to content adaptations or connections between different works.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on the word “crossover” (and closely related forms like “crossovers” or “recombination”).

    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
     Chu
    -0.83
     Tribe
    -0.75
     liberation
    -0.75
    Chou
    -0.74
    생
    -0.73
     Difference
    -0.70
    Repe
    -0.70
     snel
    -0.69
     Relationship
    -0.69
     constru
    -0.68
    POSITIVE LOGITS
     crossover
    4.34
    crossover
    3.56
     Crossover
    3.36
     cross
    2.89
     CROSS
    2.48
    cross
    2.45
    Cross
    2.42
    CROSS
    2.31
     crossing
    2.20
    交叉
    2.05
    Activations Density 0.025%

    No Known Activations