© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 98888
    Prev
    Next
    INDEX
    Explanations

    repair service

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

    The neuron activates on occurrences of the root “repair” (in any casing or morphological form).

    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
    平安
    -0.97
     мы
    -0.94
    fought
    -0.93
    蝋
    -0.93
    </h2>
    -0.93
    ectin
    -0.93
    ynomial
    -0.93
     iniciales
    -0.92
    ampingi
    -0.92
     realise
    -0.91
    POSITIVE LOGITS
     Repair
    1.65
     repair
    1.57
    repair
    1.53
     repairing
    1.38
     REPAIR
    1.31
     Repairs
    1.30
     Reparatur
    1.30
     repaired
    1.29
    Repair
    1.25
     reparar
    1.16
    Activations Density 0.013%

    No Known Activations