© 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. 69816
    Prev
    Next
    INDEX
    Explanations

    abandonment

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

    The neuron strongly activates on the concept of “abandonment” (and its forms, like “abandon,” “abandoned,” “abandonment”) in contexts such as cart-abandonment rates and abandonment costs.

    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
    Opaque
    -0.73
    鈦
    -0.69
     Tween
    -0.69
     anachron
    -0.67
    inae
    -0.66
     begrü
    -0.66
    álise
    -0.65
    ender
    -0.65
     dialysis
    -0.63
    lippery
    -0.63
    POSITIVE LOGITS
     abandoned
    5.63
     abandonment
    5.44
     abandon
    5.22
    abandon
    4.66
     Abandon
    4.63
     abandoning
    4.44
    abandoned
    4.34
     Abandoned
    4.28
    Abandon
    4.09
     aband
    3.92
    Activations Density 0.070%

    No Known Activations