© 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. 22-GEMMASCOPE-RES-131K
    7. 38757
    Prev
    Next
    INDEX
    Explanations

    tough followed by a descriptor

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

    This neuron fires on occurrences of the adjective “tough” (and its close morphological variants).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    Ꮔ
    -2.27
    乆
    -2.25
     gesamte
    -2.23
    賅
    -2.22
     срока
    -2.22
     vollständige
    -2.22
    इटम
    -2.19
    觏
    -2.19
    蒟
    -2.17
    
    -2.16
    POSITIVE LOGITS
    та
    2.58
     However
    2.53
     atau
    2.47
    蟶
    2.47
    s
    2.30
    骉
    2.13
     errori
    2.11
    〕
    2.09
     декабря
    2.06
    can
    2.00
    Activations Density 0.006%

    No Known Activations