© 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. 10-GEMMASCOPE-RES-131K
    7. 118998
    Prev
    Next
    INDEX
    Explanations

    contract and contracts

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

    The neuron fires on any occurrence of the substring “contract” (in any form or inflection).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     arbres
    -1.89
    isiert
    -1.83
    
    -1.80
     unſ
    -1.80
     avaient
    -1.77
    蚡
    -1.73
    tehende
    -1.70
    鶫
    -1.68
     kleinere
    -1.66
     锅
    -1.66
    POSITIVE LOGITS
    In
    2.34
     that
    2.11
    K
    2.08
    èdent
    2.08
    A
    2.02
    As
    1.99
    To
    1.98
    R
    1.96
    Z
    1.91
    V
    1.90
    Activations Density 0.012%

    No Known Activations