© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128047
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on terms that describe surplus or liquidation inventory and product‐condition qualifiers (e.g. leftovers, cancelled orders, B-Grade, damaged packaging, returned stock).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    previous status or condition

    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_22/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
     Purchases
    -0.82
    っけ
    -0.81
     Budgeting
    -0.80
     vůbec
    -0.80
     induc
    -0.80
     कृपया
    -0.79
    yttä
    -0.79
     unmodified
    -0.78
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.77
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.77
    POSITIVE LOGITS
     failed
    1.21
     retired
    1.05
     former
    1.05
     abandoned
    1.00
     السابق
    0.99
    failed
    0.96
     rejected
    0.93
     thất
    0.92
     других
    0.90
     fracaso
    0.88
    Activations Density 0.088%

    No Known Activations